Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.6865. Min Act: -0.1700
Data Index: 1979418 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.6240. Min Act: -0.1700
Data Index: 8195036 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.5615. Min Act: -0.1700
Data Index: 2263512 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.5302. Min Act: -0.1700
Data Index: 7886048 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4990. Min Act: -0.1700
Data Index: 7869951 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4990. Min Act: -0.1700
Data Index: 2263520 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4990. Min Act: -0.1700
Data Index: 6269481 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4364. Min Act: -0.1700
Data Index: 3633106 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4364. Min Act: -0.1700
Data Index: 4787707 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2263515 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4052. Min Act: -0.1700
Data Index: 1335202 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4052. Min Act: -0.1700
Data Index: 7573525 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4364. Min Act: -0.1700
Data Index: 8529052 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4052. Min Act: -0.1700
Data Index: 52197 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.4052. Min Act: -0.1700
Data Index: 1971620 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.3739. Min Act: -0.1700
Data Index: 7492398 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.3739. Min Act: -0.1700
Data Index: 7527014 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.3739. Min Act: -0.1700
Data Index: 2490108 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.3427. Min Act: -0.1700
Data Index: 2154707 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6865. Min Range: -4.6865
Max Act: 4.3427. Min Act: -0.1700
Data Index: 6022527 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19