Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.4542. Min Act: -0.1700
Data Index: 5740544 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.4542. Min Act: -0.1700
Data Index: 1959537 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.3917. Min Act: -0.1700
Data Index: 7879838 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.3605. Min Act: -0.1700
Data Index: 4541914 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2980. Min Act: -0.1700
Data Index: 3525776 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.3292. Min Act: -0.1700
Data Index: 6898539 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2980. Min Act: -0.1700
Data Index: 8704457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2980. Min Act: -0.1700
Data Index: 6610610 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2291477 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2175527 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2667. Min Act: -0.1700
Data Index: 735375 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2667. Min Act: -0.1700
Data Index: 1871409 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1005312 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2355. Min Act: -0.1700
Data Index: 6649196 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2355. Min Act: -0.1700
Data Index: 8340066 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1814168 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6041788 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2042. Min Act: -0.1700
Data Index: 3626695 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2042. Min Act: -0.1700
Data Index: 3630649 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4542. Min Range: -4.4542
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6338016 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19