Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0073. Min Range: -7.0073
Max Act: 7.0073. Min Act: -0.1700
Data Index: 163821 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.9135. Min Act: -0.1700
Data Index: 3369958 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.8510. Min Act: -0.1700
Data Index: 1594948 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.6010. Min Act: -0.1700
Data Index: 7170212 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.4760. Min Act: -0.1700
Data Index: 8523754 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.4448. Min Act: -0.1700
Data Index: 5358553 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.4448. Min Act: -0.1700
Data Index: 1946323 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.3823. Min Act: -0.1700
Data Index: 8104600 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.3823. Min Act: -0.1700
Data Index: 7164694 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.3510. Min Act: -0.1700
Data Index: 4529196 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.3198. Min Act: -0.1700
Data Index: 5934125 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2885. Min Act: -0.1700
Data Index: 5608425 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2573. Min Act: -0.1700
Data Index: 4177154 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2573. Min Act: -0.1700
Data Index: 3346741 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2260. Min Act: -0.1700
Data Index: 3812764 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2260. Min Act: -0.1700
Data Index: 6099512 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.1948. Min Act: -0.1700
Data Index: 1934091 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.1635. Min Act: -0.1700
Data Index: 2413857 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.2260. Min Act: -0.1700
Data Index: 724189 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0073. Min Range: -7.0073
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4328699 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19