Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.6327. Min Act: -0.1700
Data Index: 2424864 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.5077. Min Act: -0.1700
Data Index: 609406 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.3827. Min Act: -0.1700
Data Index: 8557946 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.3515. Min Act: -0.1700
Data Index: 5369746 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.2890. Min Act: -0.1700
Data Index: 7331567 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.2890. Min Act: -0.1700
Data Index: 7495137 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1952. Min Act: -0.1700
Data Index: 960169 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1952. Min Act: -0.1700
Data Index: 6807749 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1640. Min Act: -0.1700
Data Index: 695277 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1327. Min Act: -0.1700
Data Index: 7444038 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1327. Min Act: -0.1700
Data Index: 5369737 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3855804 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1327. Min Act: -0.1700
Data Index: 2738885 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.1015. Min Act: -0.1700
Data Index: 2575833 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.0702. Min Act: -0.1700
Data Index: 7387479 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.0702. Min Act: -0.1700
Data Index: 7823407 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.0390. Min Act: -0.1700
Data Index: 383694 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.0390. Min Act: -0.1700
Data Index: 747940 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6327. Min Range: -7.6327
Max Act: 7.0077. Min Act: -0.1700
Data Index: 623819 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6327. Min Range: -7.6327
Max Act: 6.9765. Min Act: -0.1700
Data Index: 678057 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19