Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.2976. Min Act: -0.1700
Data Index: 5279460 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.2351. Min Act: -0.1700
Data Index: 2453734 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.2351. Min Act: -0.1700
Data Index: 5964681 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.1101. Min Act: -0.1700
Data Index: 5975062 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.0476. Min Act: -0.1700
Data Index: 7429252 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.0476. Min Act: -0.1700
Data Index: 7133837 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4973915 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2976. Min Range: -7.2976
Max Act: 7.0163. Min Act: -0.1700
Data Index: 31017 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.9851. Min Act: -0.1700
Data Index: 1539306 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.9538. Min Act: -0.1700
Data Index: 1404585 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.9851. Min Act: -0.1700
Data Index: 1842389 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.9226. Min Act: -0.1700
Data Index: 4744679 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.8913. Min Act: -0.1700
Data Index: 4680445 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.8288. Min Act: -0.1700
Data Index: 7895115 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7976. Min Act: -0.1700
Data Index: 2577309 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7976. Min Act: -0.1700
Data Index: 7771670 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7976. Min Act: -0.1700
Data Index: 7592374 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7976. Min Act: -0.1700
Data Index: 5997370 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7663. Min Act: -0.1700
Data Index: 354829 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2976. Min Range: -7.2976
Max Act: 6.7663. Min Act: -0.1700
Data Index: 363906 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19