Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4697. Min Range: -9.4697
Max Act: 9.4697. Min Act: -0.1700
Data Index: 6652782 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.5322. Min Act: -0.1700
Data Index: 6645771 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.3447. Min Act: -0.1700
Data Index: 3996382 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.3447. Min Act: -0.1700
Data Index: 4225194 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2822. Min Act: -0.1700
Data Index: 4642508 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2509. Min Act: -0.1700
Data Index: 1599488 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2509. Min Act: -0.1700
Data Index: 3570788 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2197. Min Act: -0.1700
Data Index: 4551974 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2197. Min Act: -0.1700
Data Index: 1090029 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2197. Min Act: -0.1700
Data Index: 1090022 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2509. Min Act: -0.1700
Data Index: 3237331 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2197. Min Act: -0.1700
Data Index: 5777561 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1572. Min Act: -0.1700
Data Index: 5602785 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.2197. Min Act: -0.1700
Data Index: 6739347 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1884. Min Act: -0.1700
Data Index: 3996383 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1884. Min Act: -0.1700
Data Index: 6195749 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1572. Min Act: -0.1700
Data Index: 893102 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1884. Min Act: -0.1700
Data Index: 1378179 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1259. Min Act: -0.1700
Data Index: 3709730 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4697. Min Range: -9.4697
Max Act: 8.1572. Min Act: -0.1700
Data Index: 2662907 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19