Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3082. Min Range: -7.3082
Max Act: 7.3082. Min Act: -0.1700
Data Index: 8828417 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3082. Min Range: -7.3082
Max Act: 7.1832. Min Act: -0.1700
Data Index: 306173 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3082. Min Range: -7.3082
Max Act: 7.1520. Min Act: -0.1700
Data Index: 7712679 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3082. Min Range: -7.3082
Max Act: 7.0270. Min Act: -0.1700
Data Index: 3838257 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.9020. Min Act: -0.1700
Data Index: 7366038 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.8395. Min Act: -0.1700
Data Index: 4276857 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.8395. Min Act: -0.1700
Data Index: 6772747 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7225249 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8315485 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.7770. Min Act: -0.1700
Data Index: 1743195 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.7457. Min Act: -0.1700
Data Index: 5229344 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.7457. Min Act: -0.1700
Data Index: 5046783 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.7457. Min Act: -0.1700
Data Index: 1743286 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1514132 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6520. Min Act: -0.1700
Data Index: 4077328 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6520. Min Act: -0.1700
Data Index: 3475935 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6520. Min Act: -0.1700
Data Index: 3583982 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6520. Min Act: -0.1700
Data Index: 197414 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6207. Min Act: -0.1700
Data Index: 7324540 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3082. Min Range: -7.3082
Max Act: 6.6207. Min Act: -0.1700
Data Index: 639698 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19