Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2315. Min Range: -10.2315
Max Act: 10.2315. Min Act: -0.1700
Data Index: 8435052 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2315. Min Range: -10.2315
Max Act: 10.1690. Min Act: -0.1700
Data Index: 654389 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2315. Min Range: -10.2315
Max Act: 10.1065. Min Act: -0.1700
Data Index: 6201538 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2315. Min Range: -10.2315
Max Act: 10.0440. Min Act: -0.1700
Data Index: 5340669 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.9815. Min Act: -0.1700
Data Index: 3854290 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.9815. Min Act: -0.1700
Data Index: 5018663 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.9190. Min Act: -0.1700
Data Index: 6020559 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.9190. Min Act: -0.1700
Data Index: 1444611 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.8565. Min Act: -0.1700
Data Index: 2262700 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7940. Min Act: -0.1700
Data Index: 2305563 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7940. Min Act: -0.1700
Data Index: 7261998 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7940. Min Act: -0.1700
Data Index: 8253276 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7940. Min Act: -0.1700
Data Index: 6374822 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7315. Min Act: -0.1700
Data Index: 5365462 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.7315. Min Act: -0.1700
Data Index: 2129258 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.6690. Min Act: -0.1700
Data Index: 4213127 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.6065. Min Act: -0.1700
Data Index: 10696 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.6065. Min Act: -0.1700
Data Index: 5828412 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.5440. Min Act: -0.1700
Data Index: 55791 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2315. Min Range: -10.2315
Max Act: 9.5440. Min Act: -0.1700
Data Index: 6695560 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19