Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5109 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2042. Min Range: -7.2042
Max Act: 7.2042. Min Act: -0.1700
Data Index: 8671296 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.6417. Min Act: -0.1700
Data Index: 2528299 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.5479. Min Act: -0.1700
Data Index: 8232485 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.4854. Min Act: -0.1700
Data Index: 7160697 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.4542. Min Act: -0.1700
Data Index: 3842922 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.3917. Min Act: -0.1700
Data Index: 6156984 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.3917. Min Act: -0.1700
Data Index: 6876606 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.3292. Min Act: -0.1700
Data Index: 821037 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.3292. Min Act: -0.1700
Data Index: 4073470 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.3292. Min Act: -0.1700
Data Index: 8907 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.2667. Min Act: -0.1700
Data Index: 569489 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.2667. Min Act: -0.1700
Data Index: 8025028 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.2667. Min Act: -0.1700
Data Index: 4074154 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.2042. Min Act: -0.1700
Data Index: 5502194 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.1729. Min Act: -0.1700
Data Index: 3282806 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.1729. Min Act: -0.1700
Data Index: 2834946 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.1729. Min Act: -0.1700
Data Index: 4329469 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.2042. Min Act: -0.1700
Data Index: 3408908 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.1104. Min Act: -0.1700
Data Index: 1132795 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2042. Min Range: -7.2042
Max Act: 6.1417. Min Act: -0.1700
Data Index: 472790 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19