Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.4227. Min Act: -0.1700
Data Index: 3574078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3600. Min Act: -0.1700
Data Index: 4709955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3914. Min Act: -0.1700
Data Index: 7555237 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3286. Min Act: -0.1700
Data Index: 8070919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3286. Min Act: -0.1700
Data Index: 6175892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3286. Min Act: -0.1700
Data Index: 2437820 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.3286. Min Act: -0.1700
Data Index: 1436592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2973. Min Act: -0.1700
Data Index: 8093898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2973. Min Act: -0.1700
Data Index: 6409934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 1670455 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 1870942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 932965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2344. Min Act: -0.1700
Data Index: 6508967 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 4579543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 6537640 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2344. Min Act: -0.1700
Data Index: 7471805 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2344. Min Act: -0.1700
Data Index: 3841284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2344. Min Act: -0.1700
Data Index: 6037278 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2344. Min Act: -0.1700
Data Index: 835604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4227. Min Range: -3.4227
Max Act: 3.2659. Min Act: -0.1700
Data Index: 2677314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19