Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 403 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2657. Min Range: -6.2657
Max Act: 6.2657. Min Act: -0.1700
Data Index: 7365633 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2657. Min Range: -6.2657
Max Act: 6.0782. Min Act: -0.1700
Data Index: 3236017 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2657. Min Range: -6.2657
Max Act: 6.1095. Min Act: -0.1700
Data Index: 946670 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2657. Min Range: -6.2657
Max Act: 6.0470. Min Act: -0.1700
Data Index: 7587914 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.9845. Min Act: -0.1700
Data Index: 2483472 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.9532. Min Act: -0.1700
Data Index: 6792787 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.9532. Min Act: -0.1700
Data Index: 7644235 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.9220. Min Act: -0.1700
Data Index: 1378234 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.8907. Min Act: -0.1700
Data Index: 3147490 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.9220. Min Act: -0.1700
Data Index: 3650758 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.8595. Min Act: -0.1700
Data Index: 4288236 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.8282. Min Act: -0.1700
Data Index: 1200537 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7970. Min Act: -0.1700
Data Index: 1171368 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7970. Min Act: -0.1700
Data Index: 5503964 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7657. Min Act: -0.1700
Data Index: 6886465 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7345. Min Act: -0.1700
Data Index: 7484234 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7657. Min Act: -0.1700
Data Index: 229732 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7970. Min Act: -0.1700
Data Index: 510258 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7657. Min Act: -0.1700
Data Index: 1877858 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2657. Min Range: -6.2657
Max Act: 5.7345. Min Act: -0.1700
Data Index: 1321112 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19