Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5527 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.6420. Min Act: -0.1700
Data Index: 177293 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.6108. Min Act: -0.1700
Data Index: 1172903 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.5170. Min Act: -0.1700
Data Index: 6707402 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.4858. Min Act: -0.1700
Data Index: 1373497 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.4858. Min Act: -0.1700
Data Index: 4504350 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3380435 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3647492 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.3920. Min Act: -0.1700
Data Index: 2164500 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.3295. Min Act: -0.1700
Data Index: 5244496 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2983. Min Act: -0.1700
Data Index: 252316 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.3295. Min Act: -0.1700
Data Index: 3963142 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2983. Min Act: -0.1700
Data Index: 3727308 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2670. Min Act: -0.1700
Data Index: 22306 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2358. Min Act: -0.1700
Data Index: 3490533 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2358. Min Act: -0.1700
Data Index: 3604279 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2045. Min Act: -0.1700
Data Index: 781066 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2358. Min Act: -0.1700
Data Index: 1946539 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6458653 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2670. Min Act: -0.1700
Data Index: 1100725 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6420. Min Range: -5.6420
Max Act: 5.2358. Min Act: -0.1700
Data Index: 5168358 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19