Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.3202. Min Act: -0.1700
Data Index: 3181504 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.2265. Min Act: -0.1700
Data Index: 6433603 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 3986792 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.2265. Min Act: -0.1700
Data Index: 2286938 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.1639. Min Act: -0.1700
Data Index: 2575106 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.1639. Min Act: -0.1700
Data Index: 7192190 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.1327. Min Act: -0.1700
Data Index: 6858455 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0702. Min Act: -0.1700
Data Index: 7975914 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0702. Min Act: -0.1700
Data Index: 3939326 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0702. Min Act: -0.1700
Data Index: 5599157 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2847208 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4284436 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0389. Min Act: -0.1700
Data Index: 2572923 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0077. Min Act: -0.1700
Data Index: 3330975 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2926970 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0077. Min Act: -0.1700
Data Index: 6777447 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3202. Min Range: -4.3202
Max Act: 4.0077. Min Act: -0.1700
Data Index: 1161938 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3202. Min Range: -4.3202
Max Act: 3.9764. Min Act: -0.1700
Data Index: 6182979 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3202. Min Range: -4.3202
Max Act: 3.9608. Min Act: -0.1700
Data Index: 2117625 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3202. Min Range: -4.3202
Max Act: 3.9764. Min Act: -0.1700
Data Index: 5061300 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19