Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1682. Min Act: -0.1700
Data Index: 2333790 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1682. Min Act: -0.1700
Data Index: 7097602 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1370. Min Act: -0.1700
Data Index: 8301043 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1370. Min Act: -0.1700
Data Index: 6967565 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1057. Min Act: -0.1700
Data Index: 689947 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1057. Min Act: -0.1700
Data Index: 1700473 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 8227814 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 2630944 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1370. Min Act: -0.1700
Data Index: 5572565 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1370. Min Act: -0.1700
Data Index: 8683270 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 1962030 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1370. Min Act: -0.1700
Data Index: 8281939 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0432. Min Act: -0.1700
Data Index: 4944182 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 4470572 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.1057. Min Act: -0.1700
Data Index: 6164737 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 6717959 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 2217522 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 7126010 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 289559 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1682. Min Range: -4.1682
Max Act: 4.0745. Min Act: -0.1700
Data Index: 7614140 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19