Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5577 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1967. Min Act: -0.1700
Data Index: 4002589 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1655. Min Act: -0.1700
Data Index: 6560590 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1655. Min Act: -0.1700
Data Index: 3206781 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1342. Min Act: -0.1700
Data Index: 2377350 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1342. Min Act: -0.1700
Data Index: 1311786 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1030. Min Act: -0.1700
Data Index: 6903828 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.1030. Min Act: -0.1700
Data Index: 1577616 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.0717. Min Act: -0.1700
Data Index: 5120284 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.0717. Min Act: -0.1700
Data Index: 7340528 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.0405. Min Act: -0.1698
Data Index: 7024729 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.0717. Min Act: -0.1699
Data Index: 5126523 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1967. Min Range: -6.1967
Max Act: 6.0092. Min Act: -0.1700
Data Index: 5031774 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 5198015 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9467. Min Act: -0.1700
Data Index: 7750008 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 4922165 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 7816123 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 4981260 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 36684 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 282754 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1967. Min Range: -6.1967
Max Act: 5.9780. Min Act: -0.1700
Data Index: 44189 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19