Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6207 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.2115. Min Act: -0.1700
Data Index: 3027656 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.2115. Min Act: -0.1700
Data Index: 2521211 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0856. Min Act: -0.1700
Data Index: 7100657 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.1171. Min Act: -0.1700
Data Index: 3327995 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0856. Min Act: -0.1700
Data Index: 5702458 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0856. Min Act: -0.1700
Data Index: 5300865 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0540. Min Act: -0.1700
Data Index: 4097442 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0383. Min Act: -0.1700
Data Index: 309259 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0225. Min Act: -0.1700
Data Index: 996235 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0067. Min Act: -0.1700
Data Index: 1719974 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0067. Min Act: -0.1700
Data Index: 195753 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2115. Min Range: -3.2115
Max Act: 3.0067. Min Act: -0.1700
Data Index: 4083288 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 8169070 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 1106260 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 4817918 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9909. Min Act: -0.1700
Data Index: 57248 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 7531743 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 4210485 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 2787811 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2115. Min Range: -3.2115
Max Act: 2.9751. Min Act: -0.1700
Data Index: 1557322 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19