Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6133 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.8018. Min Act: -0.1700
Data Index: 5256091 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.5518. Min Act: -0.1700
Data Index: 3348869 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.5518. Min Act: -0.1700
Data Index: 1745073 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4580. Min Act: -0.1700
Data Index: 7784002 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4268. Min Act: -0.1700
Data Index: 3888650 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3250283 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2705. Min Act: -0.1700
Data Index: 304126 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2705. Min Act: -0.1700
Data Index: 4913868 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2705. Min Act: -0.1700
Data Index: 1135593 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2393. Min Act: -0.1700
Data Index: 2317355 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2705. Min Act: -0.1700
Data Index: 61579 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.2080. Min Act: -0.1700
Data Index: 5304207 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1768. Min Act: -0.1700
Data Index: 1816695 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1768. Min Act: -0.1700
Data Index: 7970036 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1768. Min Act: -0.1700
Data Index: 1964648 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1768. Min Act: -0.1700
Data Index: 3115729 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1455. Min Act: -0.1700
Data Index: 4027609 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1455. Min Act: -0.1699
Data Index: 622393 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1143. Min Act: -0.1700
Data Index: 146577 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.1143. Min Act: -0.1700
Data Index: 642996 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19