Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5890. Min Range: -7.5890
Max Act: 7.5890. Min Act: -0.1700
Data Index: 994743 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5890. Min Range: -7.5890
Max Act: 7.0890. Min Act: -0.1700
Data Index: 7850995 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.7140. Min Act: -0.1700
Data Index: 4102286 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.6202. Min Act: -0.1700
Data Index: 1235715 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.5890. Min Act: -0.1700
Data Index: 6833583 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.5577. Min Act: -0.1700
Data Index: 7778110 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4640. Min Act: -0.1700
Data Index: 6751427 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4640. Min Act: -0.1700
Data Index: 5878020 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 3707742 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4640. Min Act: -0.1700
Data Index: 435371 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4640. Min Act: -0.1700
Data Index: 6809983 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5884989 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 6433357 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4582815 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5505195 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4015. Min Act: -0.1700
Data Index: 3292206 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4015. Min Act: -0.1700
Data Index: 5558226 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4015. Min Act: -0.1700
Data Index: 3782199 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.4327. Min Act: -0.1700
Data Index: 7037907 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5890. Min Range: -7.5890
Max Act: 6.3702. Min Act: -0.1700
Data Index: 4446842 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19