Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1101. Min Range: -6.1101
Max Act: 6.1101. Min Act: -0.1700
Data Index: 100202 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3910458 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4765119 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.7976. Min Act: -0.1700
Data Index: 4035252 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.7038. Min Act: -0.1700
Data Index: 5700540 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.7038. Min Act: -0.1700
Data Index: 3182252 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1580471 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6413. Min Act: -0.1700
Data Index: 6517308 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5553942 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 2840304 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 247306 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 8545548 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 8225586 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 5314606 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6569153 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7002835 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6751323 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 4460243 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 879812 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1101. Min Range: -6.1101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 4213266 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19