Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.6157. Min Act: -0.1694
Data Index: 366579 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5842. Min Act: -0.1700
Data Index: 4666585 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5531. Min Act: -0.1700
Data Index: 2897427 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5454. Min Act: -0.1674
Data Index: 8037228 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5378. Min Act: -0.1700
Data Index: 3469556 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5301. Min Act: -0.1700
Data Index: 5642629 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5225. Min Act: -0.1673
Data Index: 5995590 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5074. Min Act: -0.1700
Data Index: 8454981 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5074. Min Act: -0.1700
Data Index: 4886964 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.5074. Min Act: -0.1697
Data Index: 1103527 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4999. Min Act: -0.1699
Data Index: 8792126 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4924. Min Act: -0.1689
Data Index: 3176831 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4849. Min Act: -0.1640
Data Index: 5486219 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4775. Min Act: -0.1700
Data Index: 2922647 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4775. Min Act: -0.1694
Data Index: 6184880 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4701. Min Act: -0.1699
Data Index: 3960405 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4701. Min Act: -0.1691
Data Index: 455398 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4775. Min Act: -0.1686
Data Index: 1455492 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4627. Min Act: -0.1698
Data Index: 6303520 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6157. Min Range: -0.6157
Max Act: 0.4554. Min Act: -0.1635
Data Index: 336751 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19