Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.6232. Min Act: -0.1700
Data Index: 8749768 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.4669. Min Act: -0.1700
Data Index: 3954217 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.4982. Min Act: -0.1700
Data Index: 1041684 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.4357. Min Act: -0.1700
Data Index: 8780702 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.4044. Min Act: -0.1700
Data Index: 4086947 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.2794. Min Act: -0.1700
Data Index: 1209468 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.2169. Min Act: -0.1700
Data Index: 4471382 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.2482. Min Act: -0.1700
Data Index: 4492944 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.1857. Min Act: -0.1700
Data Index: 8040058 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.1544. Min Act: -0.1700
Data Index: 3833292 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.0607. Min Act: -0.1700
Data Index: 8166494 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.0607. Min Act: -0.1700
Data Index: 795530 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.0294. Min Act: -0.1700
Data Index: 8152350 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.0294. Min Act: -0.1700
Data Index: 2518711 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6232. Min Range: -7.6232
Max Act: 7.0294. Min Act: -0.1700
Data Index: 7099009 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6232. Min Range: -7.6232
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7587860 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6232. Min Range: -7.6232
Max Act: 6.9669. Min Act: -0.1700
Data Index: 5331767 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6232. Min Range: -7.6232
Max Act: 6.9669. Min Act: -0.1700
Data Index: 7610894 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6232. Min Range: -7.6232
Max Act: 6.9669. Min Act: -0.1700
Data Index: 187251 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6232. Min Range: -7.6232
Max Act: 6.9044. Min Act: -0.1700
Data Index: 8302060 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19