Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.6100. Min Act: -0.1700
Data Index: 2013094 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.5787. Min Act: -0.1700
Data Index: 7099840 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.4225. Min Act: -0.1700
Data Index: 1413814 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.1725. Min Act: -0.1700
Data Index: 1272565 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.1412. Min Act: -0.1700
Data Index: 2232115 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1239147 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0475. Min Act: -0.1700
Data Index: 5592777 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0475. Min Act: -0.1700
Data Index: 5592778 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0162. Min Act: -0.1700
Data Index: 7735924 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0162. Min Act: -0.1700
Data Index: 3149384 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6100. Min Range: -6.6100
Max Act: 6.0162. Min Act: -0.1700
Data Index: 4035545 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.9850. Min Act: -0.1700
Data Index: 4144146 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 619436 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 4906769 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 8745394 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 7750002 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 1898913 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 120102 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 2839513 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6100. Min Range: -6.6100
Max Act: 5.8287. Min Act: -0.1700
Data Index: 109022 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19