Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.3318. Min Act: -0.1700
Data Index: 4527885 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.3006. Min Act: -0.1700
Data Index: 8438858 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.1756. Min Act: -0.1700
Data Index: 3812236 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.1443. Min Act: -0.1700
Data Index: 5320198 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.1131. Min Act: -0.1700
Data Index: 4479978 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0818. Min Act: -0.1700
Data Index: 7832944 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 3661215 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 8007086 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 8790586 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 5290608 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 2866178 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0193. Min Act: -0.1699
Data Index: 7792066 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0193. Min Act: -0.1700
Data Index: 3230571 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 8211888 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3318. Min Range: -6.3318
Max Act: 6.0506. Min Act: -0.1700
Data Index: 7032107 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 4660172 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 3763719 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 3553067 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 1698290 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3318. Min Range: -6.3318
Max Act: 5.9881. Min Act: -0.1700
Data Index: 3388217 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19