Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0470. Min Range: -6.0470
Max Act: 6.0157. Min Act: -0.1700
Data Index: 745545 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0470. Min Range: -6.0470
Max Act: 6.0470. Min Act: -0.1700
Data Index: 1569142 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.9532. Min Act: -0.1700
Data Index: 3986548 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.9220. Min Act: -0.1700
Data Index: 6542961 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.9220. Min Act: -0.1700
Data Index: 4206852 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.8907. Min Act: -0.1700
Data Index: 599516 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.8595. Min Act: -0.1700
Data Index: 8144379 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.8595. Min Act: -0.1700
Data Index: 3968592 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.8595. Min Act: -0.1700
Data Index: 8032687 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7970. Min Act: -0.1700
Data Index: 7418762 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7657. Min Act: -0.1700
Data Index: 3459112 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7657. Min Act: -0.1700
Data Index: 3025845 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7657. Min Act: -0.1700
Data Index: 7017502 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7345. Min Act: -0.1700
Data Index: 1439549 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7345. Min Act: -0.1700
Data Index: 5404833 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7032. Min Act: -0.1700
Data Index: 5699600 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7345. Min Act: -0.1700
Data Index: 2256033 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7032. Min Act: -0.1700
Data Index: 266742 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6941389 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0470. Min Range: -6.0470
Max Act: 5.7032. Min Act: -0.1700
Data Index: 6971020 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19