Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.8174. Min Act: -0.1700
Data Index: 7022211 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.7236. Min Act: -0.1700
Data Index: 1052469 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.6297. Min Act: -0.1700
Data Index: 8363050 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5984. Min Act: -0.1700
Data Index: 6820924 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5515. Min Act: -0.1700
Data Index: 958135 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5358. Min Act: -0.1700
Data Index: 193038 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5201. Min Act: -0.1700
Data Index: 1106044 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5201. Min Act: -0.1700
Data Index: 5776311 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4888. Min Act: -0.1700
Data Index: 6845293 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4732. Min Act: -0.1700
Data Index: 5890609 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.5045. Min Act: -0.1700
Data Index: 3946099 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4575. Min Act: -0.1700
Data Index: 4231025 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4732. Min Act: -0.1700
Data Index: 8071788 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4732. Min Act: -0.1700
Data Index: 287671 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4732. Min Act: -0.1700
Data Index: 2881860 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4575. Min Act: -0.1700
Data Index: 8666819 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4418. Min Act: -0.1700
Data Index: 3589929 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5540895 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4105. Min Act: -0.1700
Data Index: 4835246 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8174. Min Range: -3.8174
Max Act: 3.4105. Min Act: -0.1700
Data Index: 6042777 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19