Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.9450. Min Act: -0.1700
Data Index: 3520704 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.6950. Min Act: -0.1700
Data Index: 3941834 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.6013. Min Act: -0.1700
Data Index: 5902660 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.5075. Min Act: -0.1700
Data Index: 2310808 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.4450. Min Act: -0.1700
Data Index: 7691290 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.4450. Min Act: -0.1700
Data Index: 3588479 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.3200. Min Act: -0.1700
Data Index: 2845550 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.3513. Min Act: -0.1700
Data Index: 1746398 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.3200. Min Act: -0.1700
Data Index: 6291404 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4831974 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2575. Min Act: -0.1700
Data Index: 4748189 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2888. Min Act: -0.1700
Data Index: 6109714 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4626162 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 859240 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2575. Min Act: -0.1700
Data Index: 4725953 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2575. Min Act: -0.1700
Data Index: 1110661 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 2069732 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 2920936 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.1950. Min Act: -0.1700
Data Index: 3473720 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9450. Min Range: -6.9450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 809231 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19