Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6374 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.8032. Min Act: -0.1700
Data Index: 5514364 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 34544 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 2768777 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5845. Min Act: -0.1700
Data Index: 1455608 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 93303 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 5578778 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5532. Min Act: -0.1700
Data Index: 2032193 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 6936312 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 3037741 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2908259 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2913069 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 4787543 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 5525394 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 640128 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4282. Min Act: -0.1700
Data Index: 8699696 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4282. Min Act: -0.1700
Data Index: 93308 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4282. Min Act: -0.1700
Data Index: 8699694 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 2591796 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 5514365 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 6458628 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19