Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.6881. Min Act: -0.1700
Data Index: 5042800 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.3131. Min Act: -0.1700
Data Index: 42829 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.3131. Min Act: -0.1700
Data Index: 802343 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.3131. Min Act: -0.1700
Data Index: 4963440 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.2506. Min Act: -0.1700
Data Index: 8540771 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1881. Min Act: -0.1700
Data Index: 6436653 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1881. Min Act: -0.1700
Data Index: 1413470 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1881. Min Act: -0.1700
Data Index: 6735607 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1699
Data Index: 4419869 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 6048959 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.0631. Min Act: -0.1700
Data Index: 203087 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 2010547 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 1056153 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 3289355 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 5250563 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.1256. Min Act: -0.1700
Data Index: 757813 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.0631. Min Act: -0.1700
Data Index: 5820470 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.0006. Min Act: -0.1700
Data Index: 5832162 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.0631. Min Act: -0.1700
Data Index: 5899148 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6881. Min Range: -9.6881
Max Act: 9.0631. Min Act: -0.1700
Data Index: 2059074 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19