Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3841. Min Act: -0.1700
Data Index: 4140520 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3841. Min Act: -0.1699
Data Index: 7996480 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3753. Min Act: -0.1698
Data Index: 6681838 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3665. Min Act: -0.1693
Data Index: 5029183 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3489. Min Act: -0.1698
Data Index: 676602 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3577. Min Act: -0.1694
Data Index: 8348247 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3577. Min Act: -0.1700
Data Index: 8624327 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3489. Min Act: -0.1700
Data Index: 2914698 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3489. Min Act: -0.1700
Data Index: 72481 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3312. Min Act: -0.1700
Data Index: 8433385 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3312. Min Act: -0.1700
Data Index: 3298502 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3224. Min Act: -0.1700
Data Index: 8454832 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3224. Min Act: -0.1700
Data Index: 3039331 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3224. Min Act: -0.1700
Data Index: 5221949 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3312. Min Act: -0.1700
Data Index: 3941698 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3048. Min Act: -0.1698
Data Index: 6443029 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3048. Min Act: -0.1700
Data Index: 1050558 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3048. Min Act: -0.1694
Data Index: 6583900 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3136. Min Act: -0.1695
Data Index: 5085231 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3841. Min Range: -1.3841
Max Act: 1.3136. Min Act: -0.1700
Data Index: 417465 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19