Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.6402. Min Act: -0.1700
Data Index: 613897 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.5777. Min Act: -0.1700
Data Index: 4361883 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.4839. Min Act: -0.1700
Data Index: 1457980 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.4839. Min Act: -0.1700
Data Index: 6473328 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.4527. Min Act: -0.1700
Data Index: 761028 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.3277. Min Act: -0.1700
Data Index: 3358034 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2964. Min Act: -0.1700
Data Index: 7994076 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2964. Min Act: -0.1700
Data Index: 4511329 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2964. Min Act: -0.1700
Data Index: 4783444 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2964. Min Act: -0.1700
Data Index: 3727814 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2964. Min Act: -0.1700
Data Index: 1409150 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2339. Min Act: -0.1700
Data Index: 5663779 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2652. Min Act: -0.1700
Data Index: 8214070 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2339. Min Act: -0.1700
Data Index: 7233060 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2339. Min Act: -0.1700
Data Index: 779130 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2027. Min Act: -0.1700
Data Index: 7201668 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2027. Min Act: -0.1700
Data Index: 624272 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.2027. Min Act: -0.1700
Data Index: 5335951 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.1714. Min Act: -0.1700
Data Index: 4980659 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6402. Min Range: -4.6402
Max Act: 4.1714. Min Act: -0.1700
Data Index: 155632 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19