Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.4436. Min Act: -0.1700
Data Index: 448507 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0999. Min Act: -0.1700
Data Index: 2766896 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0686. Min Act: -0.1700
Data Index: 1249510 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0686. Min Act: -0.1700
Data Index: 3384633 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0686. Min Act: -0.1700
Data Index: 5907814 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0374. Min Act: -0.1700
Data Index: 5964081 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4436. Min Range: -6.4436
Max Act: 6.0374. Min Act: -0.1700
Data Index: 8014890 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9749. Min Act: -0.1700
Data Index: 3877580 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 725714 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 3128785 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 2873389 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 3099428 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 1367233 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 4239834 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 8773987 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 8274562 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 4088680 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 6588457 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.9124. Min Act: -0.1700
Data Index: 3327244 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4436. Min Range: -6.4436
Max Act: 5.8811. Min Act: -0.1700
Data Index: 4688328 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19