Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.1739. Min Act: -0.1700
Data Index: 1616990 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.1427. Min Act: -0.1700
Data Index: 8583689 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.1114. Min Act: -0.1700
Data Index: 5216936 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0802. Min Act: -0.1700
Data Index: 8472713 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0802. Min Act: -0.1700
Data Index: 1893200 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 5773426 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 8532117 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 8189062 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 899939 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 1103720 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0177. Min Act: -0.1700
Data Index: 1826646 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1739. Min Range: -5.1739
Max Act: 4.9864. Min Act: -0.1700
Data Index: 8057971 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0489. Min Act: -0.1700
Data Index: 7344684 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0177. Min Act: -0.1700
Data Index: 7157036 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0177. Min Act: -0.1700
Data Index: 8700495 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0177. Min Act: -0.1700
Data Index: 1219054 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1739. Min Range: -5.1739
Max Act: 5.0177. Min Act: -0.1699
Data Index: 6291246 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1739. Min Range: -5.1739
Max Act: 4.9864. Min Act: -0.1700
Data Index: 7286467 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1739. Min Range: -5.1739
Max Act: 4.9864. Min Act: -0.1700
Data Index: 7120966 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1739. Min Range: -5.1739
Max Act: 4.9864. Min Act: -0.1700
Data Index: 5553451 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19