Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.4494. Min Act: -0.1700
Data Index: 5174457 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.4182. Min Act: -0.1700
Data Index: 5123776 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.3557. Min Act: -0.1700
Data Index: 7334078 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.2932. Min Act: -0.1700
Data Index: 4427589 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.2619. Min Act: -0.1700
Data Index: 2273524 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.2932. Min Act: -0.1700
Data Index: 2354463 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.2619. Min Act: -0.1700
Data Index: 8206372 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.2619. Min Act: -0.1700
Data Index: 4783474 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4055942 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 7517923 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1994. Min Act: -0.1700
Data Index: 6346062 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4829051 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1994. Min Act: -0.1700
Data Index: 366742 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 6738720 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 6599996 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1369. Min Act: -0.1700
Data Index: 5583279 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 4316227 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 339628 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1682. Min Act: -0.1700
Data Index: 1119615 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4494. Min Range: -6.4494
Max Act: 6.1369. Min Act: -0.1700
Data Index: 2678099 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19