Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.7145. Min Act: -0.1700
Data Index: 4865473 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.6520. Min Act: -0.1700
Data Index: 6704696 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6751919 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5269. Min Act: -0.1700
Data Index: 5632384 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.4644. Min Act: -0.1700
Data Index: 717772 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.4332. Min Act: -0.1700
Data Index: 6327454 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.4332. Min Act: -0.1700
Data Index: 8137445 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.4332. Min Act: -0.1700
Data Index: 5171675 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3707. Min Act: -0.1700
Data Index: 1592870 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3707. Min Act: -0.1700
Data Index: 5565062 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3082. Min Act: -0.1700
Data Index: 8366479 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3082. Min Act: -0.1700
Data Index: 2401452 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2769. Min Act: -0.1700
Data Index: 6761504 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3082. Min Act: -0.1700
Data Index: 59235 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.3082. Min Act: -0.1700
Data Index: 7248377 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2769. Min Act: -0.1700
Data Index: 2317948 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2769. Min Act: -0.1700
Data Index: 6909683 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2769. Min Act: -0.1700
Data Index: 7149839 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2769. Min Act: -0.1700
Data Index: 6392576 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.2457. Min Act: -0.1700
Data Index: 477550 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19