Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.8718. Min Act: -0.1700
Data Index: 4180396 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.8718. Min Act: -0.1700
Data Index: 3407347 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.8093. Min Act: -0.1700
Data Index: 1879911 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.9343. Min Act: -0.1700
Data Index: 7620000 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.8718. Min Act: -0.1700
Data Index: 934176 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 3960596 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.8093. Min Act: -0.1700
Data Index: 6299967 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 6034651 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 4121570 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6218. Min Act: -0.1700
Data Index: 8704132 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 918424 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.7468. Min Act: -0.1700
Data Index: 6781285 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 5037639 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6218. Min Act: -0.1700
Data Index: 3031866 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.7468. Min Act: -0.1700
Data Index: 6278533 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.7468. Min Act: -0.1700
Data Index: 1492511 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6843. Min Act: -0.1700
Data Index: 7817130 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.5593. Min Act: -0.1700
Data Index: 748218 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.6218. Min Act: -0.1700
Data Index: 6483781 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9343. Min Range: -11.9343
Max Act: 11.5593. Min Act: -0.1700
Data Index: 6190313 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19