Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0781. Min Range: -4.0781
Max Act: 4.0781. Min Act: -0.1700
Data Index: 2147481 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0781. Min Range: -4.0781
Max Act: 4.0468. Min Act: -0.1700
Data Index: 74831 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.9843. Min Act: -0.1700
Data Index: 5236271 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.9843. Min Act: -0.1700
Data Index: 2538873 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.9843. Min Act: -0.1700
Data Index: 6453774 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.9530. Min Act: -0.1700
Data Index: 69729 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.9218. Min Act: -0.1700
Data Index: 7852522 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8905. Min Act: -0.1700
Data Index: 6710268 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8905. Min Act: -0.1700
Data Index: 7804084 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8905. Min Act: -0.1700
Data Index: 937006 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8593. Min Act: -0.1700
Data Index: 7255278 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8593. Min Act: -0.1700
Data Index: 3542378 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8905. Min Act: -0.1700
Data Index: 2023747 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8593. Min Act: -0.1700
Data Index: 4273690 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.7967. Min Act: -0.1700
Data Index: 1302068 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8280. Min Act: -0.1700
Data Index: 2732270 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8280. Min Act: -0.1700
Data Index: 7364987 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.7967. Min Act: -0.1700
Data Index: 4484163 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.7967. Min Act: -0.1700
Data Index: 4326088 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0781. Min Range: -4.0781
Max Act: 3.8593. Min Act: -0.1700
Data Index: 4108033 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19