Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 3476210 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.6780. Min Act: -0.1700
Data Index: 2214615 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.6467. Min Act: -0.1700
Data Index: 575491 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5842. Min Act: -0.1700
Data Index: 2309362 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5846130 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5453254 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 4007529 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5982078 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 4921417 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4905. Min Act: -0.1700
Data Index: 966895 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4905. Min Act: -0.1700
Data Index: 8074462 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4905. Min Act: -0.1700
Data Index: 5509381 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.5217. Min Act: -0.1700
Data Index: 1462486 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4905. Min Act: -0.1700
Data Index: 6161489 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 6147800 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 2542820 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 3054431 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 4523774 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 3410253 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4592. Min Act: -0.1700
Data Index: 128478 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19