Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.8967. Min Act: -0.1700
Data Index: 3790005 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.7717. Min Act: -0.1700
Data Index: 6130327 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.7092. Min Act: -0.1700
Data Index: 6098731 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.7092. Min Act: -0.1700
Data Index: 3945325 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.6467. Min Act: -0.1700
Data Index: 3945337 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.5217. Min Act: -0.1700
Data Index: 7395038 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.4592. Min Act: -0.1700
Data Index: 4139983 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.5217. Min Act: -0.1700
Data Index: 4502709 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.3967. Min Act: -0.1700
Data Index: 7058396 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.3967. Min Act: -0.1700
Data Index: 7447019 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.3967. Min Act: -0.1700
Data Index: 8299397 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.3342. Min Act: -0.1700
Data Index: 4965870 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.2717. Min Act: -0.1700
Data Index: 1546097 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.2717. Min Act: -0.1700
Data Index: 1909358 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.2717. Min Act: -0.1700
Data Index: 6279245 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.1467. Min Act: -0.1700
Data Index: 2991997 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.1467. Min Act: -0.1700
Data Index: 7031167 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.2092. Min Act: -0.1700
Data Index: 4944818 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.2092. Min Act: -0.1700
Data Index: 5592408 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8967. Min Range: -9.8967
Max Act: 9.1467. Min Act: -0.1700
Data Index: 1493853 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19