Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.9446. Min Act: -0.1700
Data Index: 7992998 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.9106. Min Act: -0.1700
Data Index: 4438607 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.9106. Min Act: -0.1700
Data Index: 124222 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8935. Min Act: -0.1700
Data Index: 2665908 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8935. Min Act: -0.1700
Data Index: 757881 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.9106. Min Act: -0.1700
Data Index: 3272458 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8593. Min Act: -0.1700
Data Index: 6889454 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8508. Min Act: -0.1700
Data Index: 7220000 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8593. Min Act: -0.1700
Data Index: 4301766 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8422. Min Act: -0.1700
Data Index: 3523091 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8251. Min Act: -0.1700
Data Index: 1759993 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8336. Min Act: -0.1700
Data Index: 4092881 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8251. Min Act: -0.1700
Data Index: 228873 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8336. Min Act: -0.1700
Data Index: 4599454 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8079. Min Act: -0.1700
Data Index: 7282659 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8165. Min Act: -0.1700
Data Index: 5113551 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8165. Min Act: -0.1700
Data Index: 682288 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8165. Min Act: -0.1700
Data Index: 5534812 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.8251. Min Act: -0.1700
Data Index: 8765711 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9446. Min Range: -1.9446
Max Act: 1.7993. Min Act: -0.1700
Data Index: 8588689 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19