Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3314. Min Act: -0.1700
Data Index: 8506825 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3314. Min Act: -0.1700
Data Index: 2618067 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3314. Min Act: -0.1700
Data Index: 3332047 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3002. Min Act: -0.1700
Data Index: 1236448 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3002. Min Act: -0.1700
Data Index: 3619874 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3002. Min Act: -0.1700
Data Index: 1839924 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2689. Min Act: -0.1700
Data Index: 4380713 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2689. Min Act: -0.1700
Data Index: 6648026 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2689. Min Act: -0.1700
Data Index: 4748014 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 1583780 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 4114716 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 4859838 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 3398666 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2064. Min Act: -0.1700
Data Index: 4284852 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 1404964 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2689. Min Act: -0.1700
Data Index: 7447596 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 1441736 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 8208677 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2377. Min Act: -0.1700
Data Index: 4613729 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.2064. Min Act: -0.1700
Data Index: 645447 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19