Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.3206. Min Act: -0.1700
Data Index: 423667 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.3049. Min Act: -0.1700
Data Index: 2817793 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2735. Min Act: -0.1700
Data Index: 2028360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2735. Min Act: -0.1700
Data Index: 2559929 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 4777944 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 6187180 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 1920509 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 7938807 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 3788082 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 7608116 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2578. Min Act: -0.1700
Data Index: 7462832 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 8725045 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 3252559 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 1737155 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 3429706 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 3585038 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2421. Min Act: -0.1700
Data Index: 62873 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2264. Min Act: -0.1700
Data Index: 4488345 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2264. Min Act: -0.1700
Data Index: 4556041 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.2264. Min Act: -0.1700
Data Index: 6282844 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19