Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1488 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.9933. Min Act: -0.1700
Data Index: 2214697 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.9933. Min Act: -0.1700
Data Index: 3785551 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.9933. Min Act: -0.1700
Data Index: 2684152 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.9308. Min Act: -0.1700
Data Index: 7610353 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.8683. Min Act: -0.1700
Data Index: 2893605 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.8058. Min Act: -0.1700
Data Index: 6104456 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.8058. Min Act: -0.1700
Data Index: 4858927 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 5353843 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 7032118 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 4026147 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7120. Min Act: -0.1700
Data Index: 2575304 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 3126835 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 5126336 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.6808. Min Act: -0.1700
Data Index: 5602205 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7120. Min Act: -0.1700
Data Index: 3044926 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 5761241 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7433. Min Act: -0.1700
Data Index: 3104368 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5588580 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.6808. Min Act: -0.1700
Data Index: 6919429 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9933. Min Range: -5.9933
Max Act: 5.6183. Min Act: -0.1700
Data Index: 6974877 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19