Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4561 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 2894309 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.7651. Min Act: -0.1700
Data Index: 6354845 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.7339. Min Act: -0.1700
Data Index: 263826 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.6714. Min Act: -0.1700
Data Index: 3760800 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.6401. Min Act: -0.1700
Data Index: 1692671 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.6401. Min Act: -0.1700
Data Index: 7535390 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.6089. Min Act: -0.1700
Data Index: 5626240 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.6089. Min Act: -0.1700
Data Index: 213739 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5776. Min Act: -0.1700
Data Index: 5595782 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1300995 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5464. Min Act: -0.1700
Data Index: 4208763 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3798739 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5464. Min Act: -0.1700
Data Index: 4616553 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5464. Min Act: -0.1700
Data Index: 8646910 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3326728 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5464. Min Act: -0.1700
Data Index: 5770398 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1607156 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5151. Min Act: -0.1700
Data Index: 205909 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1315697 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7964. Min Range: -5.7964
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1701300 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19