Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2321. Min Range: -6.2321
Max Act: 6.2321. Min Act: -0.1700
Data Index: 4824510 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2321. Min Range: -6.2321
Max Act: 6.0758. Min Act: -0.1700
Data Index: 2609010 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2321. Min Range: -6.2321
Max Act: 6.0446. Min Act: -0.1700
Data Index: 4515619 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2321. Min Range: -6.2321
Max Act: 6.0133. Min Act: -0.1700
Data Index: 7451602 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2321. Min Range: -6.2321
Max Act: 6.0133. Min Act: -0.1700
Data Index: 932504 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9821. Min Act: -0.1700
Data Index: 4076697 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9508. Min Act: -0.1700
Data Index: 7548516 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9508. Min Act: -0.1700
Data Index: 4824501 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9508. Min Act: -0.1700
Data Index: 284471 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9508. Min Act: -0.1700
Data Index: 3806236 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9196. Min Act: -0.1700
Data Index: 3735333 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.9196. Min Act: -0.1700
Data Index: 1965353 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8883. Min Act: -0.1700
Data Index: 1315923 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8571. Min Act: -0.1700
Data Index: 2447257 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8571. Min Act: -0.1700
Data Index: 5990611 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8883. Min Act: -0.1700
Data Index: 1621985 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8883. Min Act: -0.1700
Data Index: 5129207 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8571. Min Act: -0.1700
Data Index: 1862388 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.8571. Min Act: -0.1700
Data Index: 464084 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2321. Min Range: -6.2321
Max Act: 5.7946. Min Act: -0.1700
Data Index: 6660630 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19