Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.3206. Min Act: -0.1700
Data Index: 6676397 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.2581. Min Act: -0.1700
Data Index: 5187216 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.1331. Min Act: -0.1700
Data Index: 6891823 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.0706. Min Act: -0.1700
Data Index: 3697976 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.0081. Min Act: -0.1700
Data Index: 4978327 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3206. Min Range: -10.3206
Max Act: 10.0081. Min Act: -0.1700
Data Index: 2047860 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.9456. Min Act: -0.1700
Data Index: 1938837 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 2717833 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.9456. Min Act: -0.1700
Data Index: 1414592 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 4100821 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8206. Min Act: -0.1700
Data Index: 3182497 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1699
Data Index: 6274756 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 4854460 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 3479026 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8206. Min Act: -0.1700
Data Index: 1281163 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 7319809 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8831. Min Act: -0.1700
Data Index: 1731579 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8206. Min Act: -0.1700
Data Index: 2947585 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.7581. Min Act: -0.1700
Data Index: 1048166 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3206. Min Range: -10.3206
Max Act: 9.8206. Min Act: -0.1700
Data Index: 3845374 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19