Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.9387. Min Act: -0.1700
Data Index: 1671729 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.9075. Min Act: -0.1700
Data Index: 7403330 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.8762. Min Act: -0.1700
Data Index: 8417940 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.8762. Min Act: -0.1700
Data Index: 708511 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.8450. Min Act: -0.1700
Data Index: 8090255 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.8450. Min Act: -0.1700
Data Index: 351090 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.7200. Min Act: -0.1700
Data Index: 8772969 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.7512. Min Act: -0.1700
Data Index: 528525 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.7200. Min Act: -0.1700
Data Index: 8423856 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.7200. Min Act: -0.1700
Data Index: 1846403 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6887. Min Act: -0.1700
Data Index: 6482950 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6575. Min Act: -0.1700
Data Index: 8406803 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6575. Min Act: -0.1700
Data Index: 4048688 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6575. Min Act: -0.1700
Data Index: 2934164 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6262. Min Act: -0.1700
Data Index: 1323476 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6262. Min Act: -0.1700
Data Index: 3910009 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6262. Min Act: -0.1700
Data Index: 7332355 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6262. Min Act: -0.1700
Data Index: 6044860 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.6575. Min Act: -0.1700
Data Index: 510489 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9387. Min Range: -4.9387
Max Act: 4.5950. Min Act: -0.1700
Data Index: 3056996 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19