Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0626. Min Range: -5.0626
Max Act: 5.0626. Min Act: -0.1700
Data Index: 3006521 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.9064. Min Act: -0.1700
Data Index: 2336825 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.8439. Min Act: -0.1700
Data Index: 2773109 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.8126. Min Act: -0.1700
Data Index: 4473251 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.8126. Min Act: -0.1700
Data Index: 3462262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.7814. Min Act: -0.1700
Data Index: 3384402 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6876. Min Act: -0.1700
Data Index: 6817467 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6876. Min Act: -0.1700
Data Index: 6509569 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6876. Min Act: -0.1700
Data Index: 5469546 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6564. Min Act: -0.1700
Data Index: 1558831 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6564. Min Act: -0.1700
Data Index: 3980096 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6564. Min Act: -0.1700
Data Index: 1123588 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6564. Min Act: -0.1700
Data Index: 5061034 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6564. Min Act: -0.1700
Data Index: 6096991 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.6251. Min Act: -0.1700
Data Index: 372320 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.5939. Min Act: -0.1700
Data Index: 3884219 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.5939. Min Act: -0.1700
Data Index: 3024236 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.5939. Min Act: -0.1700
Data Index: 19945 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.5939. Min Act: -0.1700
Data Index: 6175116 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0626. Min Range: -5.0626
Max Act: 4.5939. Min Act: -0.1700
Data Index: 773623 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19