Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.7676. Min Act: -0.1700
Data Index: 4901083 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.7051. Min Act: -0.1700
Data Index: 6915668 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.5176. Min Act: -0.1700
Data Index: 1809152 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3926. Min Act: -0.1700
Data Index: 6717704 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3926. Min Act: -0.1700
Data Index: 6449053 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3926. Min Act: -0.1700
Data Index: 1694362 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 6969786 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 4585497 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 6717705 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 2576443 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 614956 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 2529394 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 6619818 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 836102 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.2676. Min Act: -0.1700
Data Index: 6624576 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.2676. Min Act: -0.1700
Data Index: 4856476 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.2676. Min Act: -0.1700
Data Index: 3104930 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.3301. Min Act: -0.1700
Data Index: 2165392 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.2676. Min Act: -0.1700
Data Index: 1950697 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7676. Min Range: -8.7676
Max Act: 8.2676. Min Act: -0.1700
Data Index: 5949655 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19