Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2158. Min Range: -6.2158
Max Act: 6.2158. Min Act: -0.1700
Data Index: 2923452 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2158. Min Range: -6.2158
Max Act: 6.1533. Min Act: -0.1700
Data Index: 2923446 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2158. Min Range: -6.2158
Max Act: 6.1533. Min Act: -0.1700
Data Index: 2448619 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.9971. Min Act: -0.1700
Data Index: 2448620 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.9346. Min Act: -0.1700
Data Index: 135982 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.9033. Min Act: -0.1700
Data Index: 3909067 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.6846. Min Act: -0.1700
Data Index: 6050026 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.6533. Min Act: -0.1700
Data Index: 4648617 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.5908. Min Act: -0.1700
Data Index: 2049116 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.5596. Min Act: -0.1700
Data Index: 4648609 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.5596. Min Act: -0.1700
Data Index: 6373049 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.5596. Min Act: -0.1700
Data Index: 6050025 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.5283. Min Act: -0.1700
Data Index: 8754871 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 1387946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 5840270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 1792125 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 1811242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 3025117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 4475802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2158. Min Range: -6.2158
Max Act: 5.4346. Min Act: -0.1700
Data Index: 878674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19