Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5808 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.4119. Min Act: -0.1700
Data Index: 3236381 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.9431. Min Act: -0.1700
Data Index: 876004 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8181. Min Act: -0.1700
Data Index: 2635488 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4980112 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.7869. Min Act: -0.1700
Data Index: 4767675 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.6619. Min Act: -0.1700
Data Index: 1404491 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.6619. Min Act: -0.1700
Data Index: 5390205 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.5369. Min Act: -0.1700
Data Index: 1645682 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.5369. Min Act: -0.1700
Data Index: 5644006 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.5369. Min Act: -0.1700
Data Index: 7359919 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3488352 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.5056. Min Act: -0.1700
Data Index: 1103663 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4744. Min Act: -0.1700
Data Index: 8505827 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4744. Min Act: -0.1700
Data Index: 3720637 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4744. Min Act: -0.1700
Data Index: 7168540 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4431. Min Act: -0.1700
Data Index: 3486039 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4744. Min Act: -0.1700
Data Index: 2049253 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4431. Min Act: -0.1700
Data Index: 2926788 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4431. Min Act: -0.1700
Data Index: 4723195 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.4431. Min Act: -0.1700
Data Index: 8464315 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19