Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2114. Min Range: -10.2114
Max Act: 10.2114. Min Act: -0.1700
Data Index: 5439588 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2114. Min Range: -10.2114
Max Act: 9.3364. Min Act: -0.1700
Data Index: 7024466 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2114. Min Range: -10.2114
Max Act: 9.2739. Min Act: -0.1700
Data Index: 7921542 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.9614. Min Act: -0.1700
Data Index: 7082978 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.7114. Min Act: -0.1700
Data Index: 518398 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.5864. Min Act: -0.1700
Data Index: 1304763 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.5239. Min Act: -0.1700
Data Index: 7197647 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.3676. Min Act: -0.1700
Data Index: 7051440 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.3051. Min Act: -0.1700
Data Index: 7839652 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.3051. Min Act: -0.1700
Data Index: 1942244 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.2426. Min Act: -0.1700
Data Index: 7082200 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1801. Min Act: -0.1700
Data Index: 3848752 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.2114. Min Act: -0.1700
Data Index: 6108912 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1801. Min Act: -0.1700
Data Index: 104440 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1801. Min Act: -0.1700
Data Index: 6741924 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1801. Min Act: -0.1700
Data Index: 6826282 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1489. Min Act: -0.1700
Data Index: 8276600 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.1176. Min Act: -0.1700
Data Index: 7466240 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.0864. Min Act: -0.1700
Data Index: 3437043 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2114. Min Range: -10.2114
Max Act: 8.0864. Min Act: -0.1700
Data Index: 5062762 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19