Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 844416 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.4651. Min Act: -0.1700
Data Index: 8321759 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.4026. Min Act: -0.1700
Data Index: 3673120 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.3401. Min Act: -0.1700
Data Index: 4015669 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.3401. Min Act: -0.1700
Data Index: 4694737 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.3714. Min Act: -0.1700
Data Index: 6576173 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.3089. Min Act: -0.1700
Data Index: 7191674 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.2776. Min Act: -0.1700
Data Index: 4651078 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.2776. Min Act: -0.1700
Data Index: 4584788 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.2151. Min Act: -0.1700
Data Index: 3081431 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.0901. Min Act: -0.1700
Data Index: 4933234 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9651. Min Range: -7.9651
Max Act: 7.0589. Min Act: -0.1700
Data Index: 6521754 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.9964. Min Act: -0.1700
Data Index: 8724479 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.9339. Min Act: -0.1700
Data Index: 8368896 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.8714. Min Act: -0.1700
Data Index: 5509034 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.9026. Min Act: -0.1700
Data Index: 8128915 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.9339. Min Act: -0.1700
Data Index: 8173996 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.8714. Min Act: -0.1700
Data Index: 1375997 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.8401. Min Act: -0.1700
Data Index: 5907613 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9651. Min Range: -7.9651
Max Act: 6.8714. Min Act: -0.1700
Data Index: 3673118 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19