Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0786. Min Range: -9.0786
Max Act: 9.0786. Min Act: -0.1699
Data Index: 6138876 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0786. Min Range: -9.0786
Max Act: 9.0161. Min Act: -0.1700
Data Index: 8303953 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.9536. Min Act: -0.1700
Data Index: 1419390 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 3105428 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.7661. Min Act: -0.1700
Data Index: 1189980 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.7661. Min Act: -0.1700
Data Index: 3815028 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.7036. Min Act: -0.1700
Data Index: 8251935 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.6411. Min Act: -0.1700
Data Index: 6934192 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.5786. Min Act: -0.1700
Data Index: 4044421 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.4536. Min Act: -0.1700
Data Index: 186044 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.4536. Min Act: -0.1700
Data Index: 405679 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.5161. Min Act: -0.1700
Data Index: 1801535 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3911. Min Act: -0.1700
Data Index: 7099822 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3911. Min Act: -0.1700
Data Index: 3531430 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3911. Min Act: -0.1699
Data Index: 1120990 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3911. Min Act: -0.1700
Data Index: 8204428 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3911. Min Act: -0.1700
Data Index: 5003683 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3286. Min Act: -0.1700
Data Index: 6798338 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3286. Min Act: -0.1700
Data Index: 8190711 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0786. Min Range: -9.0786
Max Act: 8.3286. Min Act: -0.1700
Data Index: 4211366 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19