Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 839 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.7883. Min Act: -0.1700
Data Index: 7821618 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.5383. Min Act: -0.1700
Data Index: 3811968 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.4758. Min Act: -0.1700
Data Index: 377324 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.4758. Min Act: -0.1700
Data Index: 6707355 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.4133. Min Act: -0.1700
Data Index: 442459 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.3508. Min Act: -0.1700
Data Index: 5759181 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.3508. Min Act: -0.1700
Data Index: 1625989 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.2883. Min Act: -0.1700
Data Index: 4045298 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 7530827 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 3058965 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 3993316 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.2258. Min Act: -0.1700
Data Index: 322351 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 1951783 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 7383860 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 466747 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1008. Min Act: -0.1700
Data Index: 2536581 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1008. Min Act: -0.1700
Data Index: 4537047 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1008. Min Act: -0.1700
Data Index: 783297 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1633. Min Act: -0.1700
Data Index: 7079057 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7883. Min Range: -9.7883
Max Act: 9.1008. Min Act: -0.1700
Data Index: 3696935 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19