Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3764. Min Range: -7.3764
Max Act: 7.3764. Min Act: -0.1700
Data Index: 6761734 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3764. Min Range: -7.3764
Max Act: 7.2202. Min Act: -0.1700
Data Index: 5526034 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3764. Min Range: -7.3764
Max Act: 7.0327. Min Act: -0.1700
Data Index: 1593194 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3764. Min Range: -7.3764
Max Act: 7.0014. Min Act: -0.1700
Data Index: 5287693 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8764. Min Act: -0.1700
Data Index: 272177 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2011723 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8452. Min Act: -0.1700
Data Index: 6302667 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5526298 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8139. Min Act: -0.1700
Data Index: 7509608 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6131502 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7827. Min Act: -0.1700
Data Index: 6549904 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7514. Min Act: -0.1700
Data Index: 5839023 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7202. Min Act: -0.1700
Data Index: 3466064 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7514. Min Act: -0.1700
Data Index: 2347688 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7514. Min Act: -0.1700
Data Index: 385141 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7202. Min Act: -0.1700
Data Index: 5021328 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7202. Min Act: -0.1700
Data Index: 8093571 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7202. Min Act: -0.1700
Data Index: 7836604 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.7202. Min Act: -0.1700
Data Index: 4286878 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3764. Min Range: -7.3764
Max Act: 6.6577. Min Act: -0.1700
Data Index: 6389067 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19