Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2294. Min Range: -5.2294
Max Act: 5.2294. Min Act: -0.1700
Data Index: 2056516 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2294. Min Range: -5.2294
Max Act: 5.2294. Min Act: -0.1700
Data Index: 2024919 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2294. Min Range: -5.2294
Max Act: 5.0419. Min Act: -0.1697
Data Index: 7374745 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2294. Min Range: -5.2294
Max Act: 5.0106. Min Act: -0.1700
Data Index: 2671410 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2294. Min Range: -5.2294
Max Act: 5.0106. Min Act: -0.1700
Data Index: 2938793 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9794. Min Act: -0.1700
Data Index: 424465 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9794. Min Act: -0.1700
Data Index: 3864834 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9794. Min Act: -0.1700
Data Index: 7348289 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9169. Min Act: -0.1700
Data Index: 4099948 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9169. Min Act: -0.1700
Data Index: 7432158 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.9169. Min Act: -0.1700
Data Index: 8059105 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8856. Min Act: -0.1700
Data Index: 6699673 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8856. Min Act: -0.1700
Data Index: 6789844 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 4145407 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8856. Min Act: -0.1700
Data Index: 4480620 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 5088641 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 3029034 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 6481113 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 2541602 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2294. Min Range: -5.2294
Max Act: 4.8544. Min Act: -0.1700
Data Index: 5501214 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19