Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.5961. Min Range: -16.5961
Max Act: 16.5961. Min Act: -0.1700
Data Index: 6693405 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.5961. Min Range: -16.5961
Max Act: 16.4711. Min Act: -0.1700
Data Index: 2502390 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.5961. Min Range: -16.5961
Max Act: 16.3461. Min Act: -0.1700
Data Index: 7740645 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.5961. Min Range: -16.5961
Max Act: 16.0961. Min Act: -0.1700
Data Index: 3386004 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.8461. Min Act: -0.1700
Data Index: 7340965 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.8461. Min Act: -0.1700
Data Index: 5374844 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.7211. Min Act: -0.1700
Data Index: 5686829 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.7211. Min Act: -0.1700
Data Index: 3151155 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.7211. Min Act: -0.1700
Data Index: 1091131 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5961. Min Act: -0.1700
Data Index: 6405722 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5961. Min Act: -0.1700
Data Index: 4429328 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5961. Min Act: -0.1700
Data Index: 2663078 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5961. Min Act: -0.1700
Data Index: 1014383 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5336. Min Act: -0.1700
Data Index: 2193660 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5336. Min Act: -0.1700
Data Index: 4538895 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.5336. Min Act: -0.1700
Data Index: 8404965 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.4711. Min Act: -0.1700
Data Index: 6276219 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.4086. Min Act: -0.1700
Data Index: 1421007 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.4086. Min Act: -0.1700
Data Index: 5444460 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.5961. Min Range: -16.5961
Max Act: 15.4711. Min Act: -0.1700
Data Index: 1201616 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19