Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1734554 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6001793 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.9363. Min Act: -0.1700
Data Index: 2601863 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.8894. Min Act: -0.1700
Data Index: 2251354 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.8425. Min Act: -0.1700
Data Index: 3258588 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.8112. Min Act: -0.1700
Data Index: 8021364 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6237981 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7486. Min Act: -0.1700
Data Index: 6981275 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7174. Min Act: -0.1700
Data Index: 1405793 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7486. Min Act: -0.1700
Data Index: 13026 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7330. Min Act: -0.1700
Data Index: 5795066 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7486. Min Act: -0.1700
Data Index: 3431888 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7330. Min Act: -0.1700
Data Index: 6537860 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7174. Min Act: -0.1700
Data Index: 4247777 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7017. Min Act: -0.1700
Data Index: 2230562 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.6861. Min Act: -0.1700
Data Index: 1796679 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.7017. Min Act: -0.1700
Data Index: 6027984 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.6861. Min Act: -0.1700
Data Index: 4597531 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.6861. Min Act: -0.1700
Data Index: 7235154 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9988. Min Range: -3.9988
Max Act: 3.6861. Min Act: -0.1700
Data Index: 2621421 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19