Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2999. Min Range: -8.2999
Max Act: 8.2999. Min Act: -0.1700
Data Index: 6364295 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.6749. Min Act: -0.1700
Data Index: 4390536 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.6749. Min Act: -0.1700
Data Index: 711439 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.6124. Min Act: -0.1700
Data Index: 8053074 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.6124. Min Act: -0.1700
Data Index: 8561107 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.5812. Min Act: -0.1700
Data Index: 8116533 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.5187. Min Act: -0.1700
Data Index: 5250821 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.5187. Min Act: -0.1700
Data Index: 8612720 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.4562. Min Act: -0.1700
Data Index: 426290 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.4249. Min Act: -0.1700
Data Index: 4167870 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.3624. Min Act: -0.1700
Data Index: 2997015 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.3937. Min Act: -0.1700
Data Index: 1351845 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.3312. Min Act: -0.1700
Data Index: 6835345 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.3312. Min Act: -0.1700
Data Index: 8370656 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.3312. Min Act: -0.1700
Data Index: 4457973 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.2999. Min Act: -0.1700
Data Index: 1594638 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.2999. Min Act: -0.1700
Data Index: 2888965 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.2999. Min Act: -0.1700
Data Index: 7768717 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.2687. Min Act: -0.1700
Data Index: 993420 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2999. Min Range: -8.2999
Max Act: 7.2687. Min Act: -0.1700
Data Index: 8557975 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19