Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.6619. Min Act: -0.1700
Data Index: 546702 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.6306. Min Act: -0.1700
Data Index: 7346706 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.6306. Min Act: -0.1700
Data Index: 260461 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5681. Min Act: -0.1700
Data Index: 6782893 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5994. Min Act: -0.1699
Data Index: 8524252 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5681. Min Act: -0.1700
Data Index: 861958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5681. Min Act: -0.1700
Data Index: 5383182 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5994. Min Act: -0.1700
Data Index: 3099390 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1699
Data Index: 4829868 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1699
Data Index: 8547238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1700
Data Index: 7608919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1700
Data Index: 6766336 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1700
Data Index: 189068 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5369. Min Act: -0.1700
Data Index: 1548779 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1699
Data Index: 5345076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1700
Data Index: 538056 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1699
Data Index: 3828152 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1700
Data Index: 6218422 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1700
Data Index: 6702384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.5056. Min Act: -0.1699
Data Index: 3838023 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19