Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1714 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.1140. Min Act: -0.1700
Data Index: 4750756 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0515. Min Act: -0.1700
Data Index: 4033657 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0515. Min Act: -0.1700
Data Index: 5095150 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0203. Min Act: -0.1700
Data Index: 1237575 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0203. Min Act: -0.1700
Data Index: 5034318 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0203. Min Act: -0.1698
Data Index: 7042125 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0203. Min Act: -0.1700
Data Index: 3383025 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0203. Min Act: -0.1699
Data Index: 8607655 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 312719 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4719132 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 417200 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9578. Min Act: -0.1700
Data Index: 6347538 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9265. Min Act: -0.1700
Data Index: 3076824 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9578. Min Act: -0.1699
Data Index: 2953913 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9578. Min Act: -0.1700
Data Index: 6703440 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8953. Min Act: -0.1700
Data Index: 6484644 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8953. Min Act: -0.1700
Data Index: 6861595 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8953. Min Act: -0.1700
Data Index: 4281379 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8953. Min Act: -0.1700
Data Index: 4849900 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3027549 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19