Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3941 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.2166. Min Act: -0.1700
Data Index: 928914 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1853. Min Act: -0.1700
Data Index: 190399 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1853. Min Act: -0.1700
Data Index: 7539194 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1541. Min Act: -0.1700
Data Index: 5283914 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1228. Min Act: -0.1700
Data Index: 1153602 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0916. Min Act: -0.1700
Data Index: 8184223 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.1228. Min Act: -0.1700
Data Index: 3583360 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0916. Min Act: -0.1700
Data Index: 5315845 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 5806222 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 3060788 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0291. Min Act: -0.1700
Data Index: 541807 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 8038733 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0603. Min Act: -0.1700
Data Index: 3833607 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0291. Min Act: -0.1700
Data Index: 6965442 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2166. Min Range: -4.2166
Max Act: 4.0291. Min Act: -0.1700
Data Index: 5654511 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9978. Min Act: -0.1700
Data Index: 6124978 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9978. Min Act: -0.1700
Data Index: 4171871 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9978. Min Act: -0.1700
Data Index: 724616 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9978. Min Act: -0.1700
Data Index: 6107716 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2166. Min Range: -4.2166
Max Act: 3.9978. Min Act: -0.1700
Data Index: 5707062 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19