Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.7239. Min Act: -0.1700
Data Index: 7870820 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.4114. Min Act: -0.1700
Data Index: 7090858 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.3489. Min Act: -0.1700
Data Index: 847225 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.3489. Min Act: -0.1700
Data Index: 485859 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.3489. Min Act: -0.1700
Data Index: 3847471 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.3177. Min Act: -0.1700
Data Index: 8053793 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.2864. Min Act: -0.1700
Data Index: 3278562 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.2239. Min Act: -0.1700
Data Index: 4605399 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.2239. Min Act: -0.1700
Data Index: 5128955 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1927. Min Act: -0.1700
Data Index: 3372564 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1927. Min Act: -0.1700
Data Index: 555575 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1614. Min Act: -0.1700
Data Index: 4993159 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1614. Min Act: -0.1700
Data Index: 2754626 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1614. Min Act: -0.1700
Data Index: 2875652 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1302. Min Act: -0.1700
Data Index: 4849642 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1302. Min Act: -0.1700
Data Index: 2324302 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1302. Min Act: -0.1700
Data Index: 4511777 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1302. Min Act: -0.1700
Data Index: 3041905 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1614. Min Act: -0.1700
Data Index: 1421136 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7239. Min Range: -6.7239
Max Act: 6.1302. Min Act: -0.1700
Data Index: 1174935 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19