Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.5683. Min Act: -0.1700
Data Index: 272529 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.4874. Min Act: -0.1700
Data Index: 4817305 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.4712. Min Act: -0.1700
Data Index: 2577793 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.4550. Min Act: -0.1700
Data Index: 2282354 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.4550. Min Act: -0.1700
Data Index: 5234272 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.4061. Min Act: -0.1700
Data Index: 4226051 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3571. Min Act: -0.1700
Data Index: 3792391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3571. Min Act: -0.1700
Data Index: 3989882 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3571. Min Act: -0.1700
Data Index: 2576816 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3243. Min Act: -0.1700
Data Index: 6071040 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3079. Min Act: -0.1700
Data Index: 4860557 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3079. Min Act: -0.1700
Data Index: 5494737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2914. Min Act: -0.1700
Data Index: 7181001 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2914. Min Act: -0.1700
Data Index: 235145 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.3079. Min Act: -0.1700
Data Index: 4532855 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2749. Min Act: -0.1700
Data Index: 3263776 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2749. Min Act: -0.1700
Data Index: 3951588 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2749. Min Act: -0.1700
Data Index: 2142505 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2749. Min Act: -0.1700
Data Index: 1116461 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5683. Min Range: -2.5683
Max Act: 2.2749. Min Act: -0.1700
Data Index: 2893593 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19