Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2136. Min Range: -7.2136
Max Act: 7.2136. Min Act: -0.1700
Data Index: 1599227 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.9948. Min Act: -0.1700
Data Index: 3818237 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.9636. Min Act: -0.1700
Data Index: 3952893 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.8386. Min Act: -0.1700
Data Index: 5465823 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1131979 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.8073. Min Act: -0.1700
Data Index: 6033380 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.8073. Min Act: -0.1700
Data Index: 3241982 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.8073. Min Act: -0.1700
Data Index: 8511177 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7761. Min Act: -0.1700
Data Index: 1430448 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 2686703 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7761. Min Act: -0.1700
Data Index: 635898 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7761. Min Act: -0.1700
Data Index: 7141878 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7136. Min Act: -0.1700
Data Index: 1616851 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 8536027 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 2978107 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 3427030 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 3706806 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7448. Min Act: -0.1700
Data Index: 1837450 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7761. Min Act: -0.1700
Data Index: 8056273 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2136. Min Range: -7.2136
Max Act: 6.7136. Min Act: -0.1700
Data Index: 5541772 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19