Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2819. Min Act: -0.1700
Data Index: 1228556 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.8756. Min Act: -0.1700
Data Index: 8825345 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7817. Min Act: -0.1700
Data Index: 2991740 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.8443. Min Act: -0.1700
Data Index: 6223907 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.8130. Min Act: -0.1700
Data Index: 4231079 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.8130. Min Act: -0.1700
Data Index: 6485849 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7661. Min Act: -0.1700
Data Index: 516088 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7817. Min Act: -0.1700
Data Index: 3881163 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7348. Min Act: -0.1700
Data Index: 3781517 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7505. Min Act: -0.1700
Data Index: 5677273 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7348. Min Act: -0.1700
Data Index: 3879725 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7192. Min Act: -0.1700
Data Index: 7433773 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7348. Min Act: -0.1700
Data Index: 5997930 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7348. Min Act: -0.1700
Data Index: 2962275 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7035. Min Act: -0.1700
Data Index: 1480165 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7035. Min Act: -0.1700
Data Index: 3371865 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7348. Min Act: -0.1700
Data Index: 2224537 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7192. Min Act: -0.1700
Data Index: 8589039 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7192. Min Act: -0.1700
Data Index: 8508523 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2819. Min Range: -4.2819
Max Act: 3.7192. Min Act: -0.1700
Data Index: 4431061 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19