Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5900 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.8982. Min Act: -0.1700
Data Index: 7517979 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.8670. Min Act: -0.1700
Data Index: 7797117 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.8357. Min Act: -0.1700
Data Index: 1671349 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.7732. Min Act: -0.1700
Data Index: 3491380 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.8045. Min Act: -0.1700
Data Index: 4183789 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.7732. Min Act: -0.1700
Data Index: 4527753 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2593878 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.6482. Min Act: -0.1700
Data Index: 11105 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.6482. Min Act: -0.1700
Data Index: 6295238 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.5857. Min Act: -0.1700
Data Index: 5268336 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.5545. Min Act: -0.1700
Data Index: 2726325 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.5232. Min Act: -0.1700
Data Index: 1120051 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.5232. Min Act: -0.1700
Data Index: 3970563 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.5232. Min Act: -0.1700
Data Index: 6343062 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4920. Min Act: -0.1700
Data Index: 1979800 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4607. Min Act: -0.1700
Data Index: 2870201 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4607. Min Act: -0.1700
Data Index: 2670193 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7086132 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4607. Min Act: -0.1700
Data Index: 3755330 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8982. Min Range: -6.8982
Max Act: 6.4607. Min Act: -0.1700
Data Index: 1113090 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19