Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.7362. Min Act: -0.1700
Data Index: 4767530 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.6424. Min Act: -0.1700
Data Index: 8690264 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.4549. Min Act: -0.1700
Data Index: 1969472 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.3924. Min Act: -0.1700
Data Index: 3046433 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.3299. Min Act: -0.1700
Data Index: 7943726 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.2987. Min Act: -0.1700
Data Index: 8470376 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3600915 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.2049. Min Act: -0.1700
Data Index: 2247432 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.2049. Min Act: -0.1700
Data Index: 7231568 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.1424. Min Act: -0.1700
Data Index: 3422719 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.1424. Min Act: -0.1700
Data Index: 6649306 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.1424. Min Act: -0.1700
Data Index: 7021158 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.1112. Min Act: -0.1700
Data Index: 4480157 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4623480 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0799. Min Act: -0.1700
Data Index: 8508186 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0487. Min Act: -0.1700
Data Index: 237358 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0487. Min Act: -0.1700
Data Index: 2860080 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4598020 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0487. Min Act: -0.1700
Data Index: 621585 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7362. Min Range: -5.7362
Max Act: 5.0174. Min Act: -0.1700
Data Index: 1768607 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19