Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.7413. Min Act: -0.1700
Data Index: 5302589 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.6163. Min Act: -0.1700
Data Index: 8171445 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6423017 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5538. Min Act: -0.1700
Data Index: 2406992 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5226. Min Act: -0.1700
Data Index: 254661 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5226. Min Act: -0.1700
Data Index: 1170201 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5226. Min Act: -0.1700
Data Index: 1527934 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.5538. Min Act: -0.1700
Data Index: 5666588 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4601. Min Act: -0.1700
Data Index: 3510803 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4913. Min Act: -0.1700
Data Index: 6948814 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4601. Min Act: -0.1700
Data Index: 8503198 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4601. Min Act: -0.1700
Data Index: 5396111 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4601. Min Act: -0.1700
Data Index: 253716 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4288. Min Act: -0.1700
Data Index: 2597087 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.4288. Min Act: -0.1700
Data Index: 1837556 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.3976. Min Act: -0.1700
Data Index: 7248247 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.3976. Min Act: -0.1700
Data Index: 7668962 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3887086 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.3976. Min Act: -0.1700
Data Index: 2786361 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7413. Min Range: -5.7413
Max Act: 5.3663. Min Act: -0.1700
Data Index: 5307288 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19