Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.1156. Min Act: -0.1700
Data Index: 1835290 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0821. Min Act: -0.1700
Data Index: 4158838 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0653. Min Act: -0.1700
Data Index: 4148078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0653. Min Act: -0.1700
Data Index: 3760438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0653. Min Act: -0.1700
Data Index: 3655786 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0316. Min Act: -0.1700
Data Index: 1209894 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0316. Min Act: -0.1700
Data Index: 3440556 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1156. Min Range: -2.1156
Max Act: 2.0316. Min Act: -0.1700
Data Index: 6467068 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9810. Min Act: -0.1700
Data Index: 758575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9810. Min Act: -0.1700
Data Index: 2962230 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9810. Min Act: -0.1700
Data Index: 8735524 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9640. Min Act: -0.1700
Data Index: 6305109 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9810. Min Act: -0.1700
Data Index: 1247805 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9810. Min Act: -0.1700
Data Index: 7208696 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9640. Min Act: -0.1700
Data Index: 3062019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9640. Min Act: -0.1700
Data Index: 3846856 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9386. Min Act: -0.1700
Data Index: 5983765 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9386. Min Act: -0.1700
Data Index: 7420186 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9386. Min Act: -0.1700
Data Index: 829777 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1156. Min Range: -2.1156
Max Act: 1.9301. Min Act: -0.1700
Data Index: 3856512 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19