Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0224. Min Range: -5.0224
Max Act: 5.0224. Min Act: -0.1700
Data Index: 2269292 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.8349. Min Act: -0.1700
Data Index: 2370640 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.8349. Min Act: -0.1700
Data Index: 5465436 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.7724. Min Act: -0.1700
Data Index: 59934 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.7412. Min Act: -0.1700
Data Index: 632808 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.7724. Min Act: -0.1700
Data Index: 3235152 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.7724. Min Act: -0.1700
Data Index: 6427624 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1606475 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6787. Min Act: -0.1700
Data Index: 6999182 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6787. Min Act: -0.1700
Data Index: 6103525 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6474. Min Act: -0.1700
Data Index: 5724046 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6474. Min Act: -0.1700
Data Index: 574325 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6474. Min Act: -0.1700
Data Index: 5390964 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6474. Min Act: -0.1700
Data Index: 4544464 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6787. Min Act: -0.1700
Data Index: 5546947 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6162. Min Act: -0.1700
Data Index: 5197302 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6162. Min Act: -0.1700
Data Index: 2191486 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6162. Min Act: -0.1700
Data Index: 3059013 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6162. Min Act: -0.1700
Data Index: 2432414 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0224. Min Range: -5.0224
Max Act: 4.6162. Min Act: -0.1700
Data Index: 111767 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19