Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2250 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.7804. Min Act: -0.1700
Data Index: 432525 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.7179. Min Act: -0.1700
Data Index: 4186238 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.6867. Min Act: -0.1700
Data Index: 7805496 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.4992. Min Act: -0.1700
Data Index: 6342992 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4740753 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.3742. Min Act: -0.1700
Data Index: 6776278 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.3429. Min Act: -0.1700
Data Index: 4701908 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.3429. Min Act: -0.1700
Data Index: 1715735 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.3117. Min Act: -0.1700
Data Index: 2190524 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2804. Min Act: -0.1700
Data Index: 2258106 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2492. Min Act: -0.1700
Data Index: 6106483 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2804. Min Act: -0.1700
Data Index: 5044872 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2492. Min Act: -0.1700
Data Index: 1543675 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2492. Min Act: -0.1700
Data Index: 2344638 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.2179. Min Act: -0.1700
Data Index: 823733 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5404136 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.1554. Min Act: -0.1700
Data Index: 4135984 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.1554. Min Act: -0.1700
Data Index: 571882 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.1242. Min Act: -0.1700
Data Index: 5582037 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7804. Min Range: -5.7804
Max Act: 5.1242. Min Act: -0.1700
Data Index: 5785968 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19