Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.7475. Min Act: -0.1700
Data Index: 7320399 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.6225. Min Act: -0.1700
Data Index: 3964064 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.4975. Min Act: -0.1700
Data Index: 3224260 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.4975. Min Act: -0.1700
Data Index: 2564447 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.4350. Min Act: -0.1700
Data Index: 723065 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3725. Min Act: -0.1700
Data Index: 6126472 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3725. Min Act: -0.1700
Data Index: 3035216 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3725. Min Act: -0.1700
Data Index: 1986013 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3412. Min Act: -0.1700
Data Index: 7197303 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3412. Min Act: -0.1700
Data Index: 1131558 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3412. Min Act: -0.1700
Data Index: 3717489 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3412. Min Act: -0.1700
Data Index: 1033985 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3100. Min Act: -0.1700
Data Index: 203263 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.3100. Min Act: -0.1700
Data Index: 2193081 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2787. Min Act: -0.1700
Data Index: 809653 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2475. Min Act: -0.1700
Data Index: 1137207 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2475. Min Act: -0.1700
Data Index: 3110668 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2162. Min Act: -0.1700
Data Index: 3318861 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2162. Min Act: -0.1700
Data Index: 6915474 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7475. Min Range: -7.7475
Max Act: 7.2162. Min Act: -0.1700
Data Index: 4417754 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19