Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4258 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.6291. Min Act: -0.1700
Data Index: 61059 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.4416. Min Act: -0.1700
Data Index: 7666600 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.4416. Min Act: -0.1700
Data Index: 8691238 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.2540. Min Act: -0.1700
Data Index: 3977205 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.2228. Min Act: -0.1700
Data Index: 4676770 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.1915. Min Act: -0.1700
Data Index: 3062564 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.1603. Min Act: -0.1700
Data Index: 6567989 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.1603. Min Act: -0.1700
Data Index: 8581231 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.1603. Min Act: -0.1700
Data Index: 7253907 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.1290. Min Act: -0.1700
Data Index: 1058842 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0978. Min Act: -0.1700
Data Index: 4587877 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0978. Min Act: -0.1700
Data Index: 993701 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0978. Min Act: -0.1700
Data Index: 4221957 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0665. Min Act: -0.1700
Data Index: 1058845 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0665. Min Act: -0.1700
Data Index: 3977207 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0352. Min Act: -0.1700
Data Index: 7792989 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0352. Min Act: -0.1700
Data Index: 7043722 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0352. Min Act: -0.1700
Data Index: 6188020 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0352. Min Act: -0.1700
Data Index: 7024016 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6291. Min Range: -4.6291
Max Act: 4.0352. Min Act: -0.1700
Data Index: 4367015 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19