Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3512. Min Range: -7.3512
Max Act: 7.3512. Min Act: -0.1700
Data Index: 2651052 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.9762. Min Act: -0.1700
Data Index: 1901288 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.8824. Min Act: -0.1700
Data Index: 6490796 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.8512. Min Act: -0.1700
Data Index: 8338640 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.8824. Min Act: -0.1700
Data Index: 8093938 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.8512. Min Act: -0.1700
Data Index: 1839968 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.7887. Min Act: -0.1700
Data Index: 1955416 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.7574. Min Act: -0.1700
Data Index: 1994077 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6637. Min Act: -0.1700
Data Index: 6085433 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6637. Min Act: -0.1700
Data Index: 665650 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6324. Min Act: -0.1700
Data Index: 7957649 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6637. Min Act: -0.1700
Data Index: 1378739 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6324. Min Act: -0.1700
Data Index: 6537107 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6012. Min Act: -0.1700
Data Index: 4029085 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6012. Min Act: -0.1700
Data Index: 829933 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.6012. Min Act: -0.1700
Data Index: 7115781 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.5699. Min Act: -0.1700
Data Index: 6627009 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.5699. Min Act: -0.1700
Data Index: 814976 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.5699. Min Act: -0.1700
Data Index: 5627546 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3512. Min Range: -7.3512
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3656823 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19