Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2293 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.3911. Min Range: -13.3911
Max Act: 13.3911. Min Act: -0.1700
Data Index: 195173 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.3911. Min Range: -13.3911
Max Act: 12.5161. Min Act: -0.1700
Data Index: 1797930 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.3911. Min Range: -13.3911
Max Act: 12.0786. Min Act: -0.1700
Data Index: 8561946 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.3911. Min Range: -13.3911
Max Act: 12.0786. Min Act: -0.1700
Data Index: 1686968 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.3911. Min Range: -13.3911
Max Act: 12.0161. Min Act: -0.1700
Data Index: 1257270 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.3911. Min Range: -13.3911
Max Act: 12.0161. Min Act: -0.1700
Data Index: 8540199 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.9536. Min Act: -0.1700
Data Index: 3981577 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.9536. Min Act: -0.1700
Data Index: 7186958 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.8911. Min Act: -0.1700
Data Index: 624158 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.8286. Min Act: -0.1700
Data Index: 4059924 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.8286. Min Act: -0.1700
Data Index: 1283177 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.8286. Min Act: -0.1700
Data Index: 7034731 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.7661. Min Act: -0.1700
Data Index: 3244741 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.7661. Min Act: -0.1700
Data Index: 1818408 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.7036. Min Act: -0.1700
Data Index: 1818405 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.7036. Min Act: -0.1700
Data Index: 6445426 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.7036. Min Act: -0.1700
Data Index: 5188192 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.6411. Min Act: -0.1700
Data Index: 2521069 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.6411. Min Act: -0.1700
Data Index: 7587949 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.3911. Min Range: -13.3911
Max Act: 11.6411. Min Act: -0.1700
Data Index: 1478604 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19