Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2757. Min Act: -0.1700
Data Index: 5835762 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2757. Min Act: -0.1700
Data Index: 672885 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.3070. Min Act: -0.1700
Data Index: 672884 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2757. Min Act: -0.1700
Data Index: 2086429 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2757. Min Act: -0.1700
Data Index: 4819379 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2445. Min Act: -0.1700
Data Index: 672883 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2757. Min Act: -0.1700
Data Index: 8450628 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2132. Min Act: -0.1700
Data Index: 2582574 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2132. Min Act: -0.1700
Data Index: 7742068 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1820. Min Act: -0.1700
Data Index: 8525302 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3570519 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.2132. Min Act: -0.1700
Data Index: 6492857 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 4749307 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 755747 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 694798 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 358590 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 5740751 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 5921920 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1820. Min Act: -0.1700
Data Index: 6286247 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3070. Min Range: -4.3070
Max Act: 4.1507. Min Act: -0.1700
Data Index: 6645599 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19