Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3652. Min Act: -0.1691
Data Index: 1465263 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3652. Min Act: -0.1691
Data Index: 8395025 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3387. Min Act: -0.1691
Data Index: 5152807 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3299. Min Act: -0.1691
Data Index: 3035324 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3299. Min Act: -0.1691
Data Index: 1488565 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3211. Min Act: -0.1691
Data Index: 723636 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3122. Min Act: -0.1691
Data Index: 3192998 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3122. Min Act: -0.1696
Data Index: 1413458 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3122. Min Act: -0.1691
Data Index: 65814 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3034. Min Act: -0.1691
Data Index: 6256954 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3034. Min Act: -0.1691
Data Index: 256812 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1691
Data Index: 3338632 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3034. Min Act: -0.1696
Data Index: 7639968 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.3034. Min Act: -0.1691
Data Index: 2202758 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1691
Data Index: 6525249 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2858. Min Act: -0.1691
Data Index: 8237544 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1691
Data Index: 362643 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1691
Data Index: 4104645 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1691
Data Index: 6232535 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3652. Min Range: -1.3652
Max Act: 1.2946. Min Act: -0.1692
Data Index: 2390085 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19