Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.4434. Min Act: -0.1700
Data Index: 773555 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.3496. Min Act: -0.1700
Data Index: 6592448 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.2246. Min Act: -0.1700
Data Index: 4063809 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.1621. Min Act: -0.1700
Data Index: 1260449 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.1621. Min Act: -0.1700
Data Index: 6395059 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.1621. Min Act: -0.1700
Data Index: 1522471 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.1621. Min Act: -0.1700
Data Index: 8376203 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0996. Min Act: -0.1700
Data Index: 29016 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0996. Min Act: -0.1700
Data Index: 940221 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0996. Min Act: -0.1700
Data Index: 7162268 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.1309. Min Act: -0.1700
Data Index: 2480619 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1712047 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0684. Min Act: -0.1700
Data Index: 6045247 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0684. Min Act: -0.1700
Data Index: 5152719 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0371. Min Act: -0.1700
Data Index: 1908787 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0371. Min Act: -0.1700
Data Index: 1548597 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0371. Min Act: -0.1700
Data Index: 7124349 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0059. Min Act: -0.1700
Data Index: 4826150 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0059. Min Act: -0.1700
Data Index: 466489 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4434. Min Range: -6.4434
Max Act: 6.0059. Min Act: -0.1700
Data Index: 1301397 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19