Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.7469. Min Act: -0.1700
Data Index: 6685544 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.4969. Min Act: -0.1700
Data Index: 29299 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.4969. Min Act: -0.1700
Data Index: 7429718 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.4344. Min Act: -0.1700
Data Index: 6322767 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.4344. Min Act: -0.1700
Data Index: 118070 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.3407. Min Act: -0.1700
Data Index: 7222128 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3439293 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.3407. Min Act: -0.1700
Data Index: 4608676 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2782. Min Act: -0.1700
Data Index: 4827278 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.3094. Min Act: -0.1700
Data Index: 8555719 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2469. Min Act: -0.1700
Data Index: 8752946 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2469. Min Act: -0.1700
Data Index: 1855779 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2469. Min Act: -0.1700
Data Index: 2971857 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2157. Min Act: -0.1700
Data Index: 3135864 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2157. Min Act: -0.1700
Data Index: 7816757 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2157. Min Act: -0.1700
Data Index: 5966398 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.2157. Min Act: -0.1700
Data Index: 1338018 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.1844. Min Act: -0.1700
Data Index: 495702 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.1532. Min Act: -0.1700
Data Index: 5827749 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7469. Min Range: -6.7469
Max Act: 6.1219. Min Act: -0.1700
Data Index: 7906968 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19