Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4183 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7203. Min Act: -0.1700
Data Index: 5598974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7203. Min Act: -0.1700
Data Index: 5157790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7203. Min Act: -0.1700
Data Index: 5209838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7043. Min Act: -0.1700
Data Index: 3138373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 6830252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7043. Min Act: -0.1700
Data Index: 1967421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7043. Min Act: -0.1700
Data Index: 8131139 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 1527441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 2154221 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 3043181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 8765800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6723. Min Act: -0.1700
Data Index: 2681196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 8646401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7846154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7232503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.7043. Min Act: -0.1700
Data Index: 2368257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7162841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6883. Min Act: -0.1700
Data Index: 2260439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6723. Min Act: -0.1700
Data Index: 1211470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7203. Min Range: -2.7203
Max Act: 2.6723. Min Act: -0.1700
Data Index: 2177262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19