Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.4385. Min Act: -0.1700
Data Index: 8198286 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3760. Min Act: -0.1700
Data Index: 2505289 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3760. Min Act: -0.1700
Data Index: 2891197 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3760. Min Act: -0.1700
Data Index: 8014297 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3135. Min Act: -0.1700
Data Index: 4245918 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3135. Min Act: -0.1700
Data Index: 6895348 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3135. Min Act: -0.1700
Data Index: 5320938 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3135. Min Act: -0.1700
Data Index: 4507787 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.3135. Min Act: -0.1700
Data Index: 7931548 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 3021527 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 979477 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 6681367 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 6782491 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 3898446 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.2510. Min Act: -0.1700
Data Index: 7250456 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.1885. Min Act: -0.1700
Data Index: 92138 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.1260. Min Act: -0.1700
Data Index: 6121464 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.1260. Min Act: -0.1700
Data Index: 2622929 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.0635. Min Act: -0.1700
Data Index: 809934 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4385. Min Range: -9.4385
Max Act: 9.0635. Min Act: -0.1700
Data Index: 3170370 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19