Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5064 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.1270. Min Act: -0.1700
Data Index: 8185935 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0958. Min Act: -0.1700
Data Index: 4758294 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0958. Min Act: -0.1700
Data Index: 4772528 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0958. Min Act: -0.1700
Data Index: 2211862 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0645. Min Act: -0.1700
Data Index: 5993551 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0333. Min Act: -0.1700
Data Index: 3658135 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0489. Min Act: -0.1700
Data Index: 7925924 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0489. Min Act: -0.1700
Data Index: 6254909 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1270. Min Range: -4.1270
Max Act: 4.0020. Min Act: -0.1700
Data Index: 908406 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9864. Min Act: -0.1700
Data Index: 2959867 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9864. Min Act: -0.1700
Data Index: 5648323 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9864. Min Act: -0.1700
Data Index: 5974833 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1986775 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9707. Min Act: -0.1700
Data Index: 3324684 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9551. Min Act: -0.1700
Data Index: 2822326 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1988610 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9239. Min Act: -0.1700
Data Index: 7079458 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9395. Min Act: -0.1700
Data Index: 6657754 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9239. Min Act: -0.1700
Data Index: 7022858 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1270. Min Range: -4.1270
Max Act: 3.9395. Min Act: -0.1700
Data Index: 3173703 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19