Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.6395. Min Act: -0.1700
Data Index: 2008952 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.7020. Min Act: -0.1700
Data Index: 467171 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.4520. Min Act: -0.1700
Data Index: 551676 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.3895. Min Act: -0.1700
Data Index: 2213108 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.3270. Min Act: -0.1700
Data Index: 2008953 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 2467163 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.3270. Min Act: -0.1700
Data Index: 5768697 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 5080805 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.3270. Min Act: -0.1700
Data Index: 5060406 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 2154941 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 6149467 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 2954469 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 212792 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 2170302 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 642088 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 3392319 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2645. Min Act: -0.1700
Data Index: 2485694 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 879123 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 9670 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7020. Min Range: -9.7020
Max Act: 9.2020. Min Act: -0.1700
Data Index: 2429920 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19