Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5535 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1159. Min Range: -7.1159
Max Act: 7.1159. Min Act: -0.1700
Data Index: 5470443 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1159. Min Range: -7.1159
Max Act: 7.0222. Min Act: -0.1700
Data Index: 8772299 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.8034. Min Act: -0.1700
Data Index: 7555726 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.7409. Min Act: -0.1700
Data Index: 6855075 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.7097. Min Act: -0.1700
Data Index: 3686501 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.6784. Min Act: -0.1700
Data Index: 725160 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.6784. Min Act: -0.1700
Data Index: 2821527 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.6159. Min Act: -0.1700
Data Index: 2778380 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.6159. Min Act: -0.1700
Data Index: 4421673 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5847. Min Act: -0.1700
Data Index: 5358931 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.6159. Min Act: -0.1700
Data Index: 6145524 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5847. Min Act: -0.1700
Data Index: 2944735 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5534. Min Act: -0.1700
Data Index: 8456901 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5847. Min Act: -0.1700
Data Index: 3229260 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5534. Min Act: -0.1700
Data Index: 1458653 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5534. Min Act: -0.1700
Data Index: 2074672 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5534. Min Act: -0.1700
Data Index: 5077115 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5222. Min Act: -0.1700
Data Index: 7814021 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5222. Min Act: -0.1700
Data Index: 2765688 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1159. Min Range: -7.1159
Max Act: 6.5222. Min Act: -0.1700
Data Index: 6493345 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19