Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0269. Min Range: -6.0269
Max Act: 6.0269. Min Act: -0.1700
Data Index: 3944828 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6841748 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.9332. Min Act: -0.1700
Data Index: 7472971 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8707. Min Act: -0.1700
Data Index: 7801610 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8394. Min Act: -0.1700
Data Index: 3383679 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8707. Min Act: -0.1700
Data Index: 6737747 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1375983 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8082. Min Act: -0.1700
Data Index: 6708082 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 3461175 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.8082. Min Act: -0.1700
Data Index: 2174953 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7769. Min Act: -0.1700
Data Index: 1989819 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 8211546 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7769. Min Act: -0.1700
Data Index: 5747903 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 1130957 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 8060431 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7144. Min Act: -0.1700
Data Index: 288773 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 1435109 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7144. Min Act: -0.1700
Data Index: 8234860 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 2608124 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0269. Min Range: -6.0269
Max Act: 5.7457. Min Act: -0.1700
Data Index: 4208961 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19