Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.5668. Min Act: -0.1700
Data Index: 5127054 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.3793. Min Act: -0.1700
Data Index: 2938247 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.3793. Min Act: -0.1700
Data Index: 3955827 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.2543. Min Act: -0.1700
Data Index: 6709080 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.2543. Min Act: -0.1700
Data Index: 1085666 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1918. Min Act: -0.1700
Data Index: 2858909 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1918. Min Act: -0.1700
Data Index: 8519942 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 3697324 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 6530160 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 3981299 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 5976676 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 4852814 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.1293. Min Act: -0.1700
Data Index: 6443318 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0668. Min Act: -0.1700
Data Index: 3185536 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0668. Min Act: -0.1700
Data Index: 645479 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0668. Min Act: -0.1700
Data Index: 8402867 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0668. Min Act: -0.1700
Data Index: 6722790 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0043. Min Act: -0.1700
Data Index: 7056663 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0043. Min Act: -0.1700
Data Index: 461292 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5668. Min Range: -9.5668
Max Act: 9.0043. Min Act: -0.1700
Data Index: 8157459 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19