Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.6372. Min Act: -0.1700
Data Index: 3010868 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.5747. Min Act: -0.1700
Data Index: 1252828 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.5122. Min Act: -0.1700
Data Index: 3862344 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.4497. Min Act: -0.1700
Data Index: 2137667 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.4497. Min Act: -0.1700
Data Index: 151836 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.4184. Min Act: -0.1700
Data Index: 3940312 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.4184. Min Act: -0.1700
Data Index: 2676008 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.3872. Min Act: -0.1700
Data Index: 8172771 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.3872. Min Act: -0.1700
Data Index: 7207025 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.3559. Min Act: -0.1700
Data Index: 4746631 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.3247. Min Act: -0.1700
Data Index: 30683 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.3247. Min Act: -0.1700
Data Index: 470962 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2622. Min Act: -0.1700
Data Index: 6756383 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2622. Min Act: -0.1700
Data Index: 4025216 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2309. Min Act: -0.1700
Data Index: 995674 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2309. Min Act: -0.1700
Data Index: 3543737 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2309. Min Act: -0.1700
Data Index: 662767 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2309. Min Act: -0.1700
Data Index: 5202455 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.2309. Min Act: -0.1700
Data Index: 1210173 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6372. Min Range: -7.6372
Max Act: 7.1997. Min Act: -0.1700
Data Index: 7004653 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19