Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.9623. Min Act: -0.1700
Data Index: 4387253 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.9310. Min Act: -0.1700
Data Index: 60782 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.9310. Min Act: -0.1700
Data Index: 5759592 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.9310. Min Act: -0.1700
Data Index: 3397516 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8997. Min Act: -0.1700
Data Index: 4971222 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8997. Min Act: -0.1700
Data Index: 6063619 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8685. Min Act: -0.1700
Data Index: 7661216 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8372. Min Act: -0.1700
Data Index: 7710396 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8372. Min Act: -0.1700
Data Index: 4981759 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7747. Min Act: -0.1700
Data Index: 4518236 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8059. Min Act: -0.1700
Data Index: 7999911 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8059. Min Act: -0.1700
Data Index: 1938813 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8059. Min Act: -0.1700
Data Index: 2643336 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8059. Min Act: -0.1700
Data Index: 529811 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.8059. Min Act: -0.1700
Data Index: 7513011 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7747. Min Act: -0.1700
Data Index: 6404638 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7747. Min Act: -0.1700
Data Index: 4866343 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7434. Min Act: -0.1700
Data Index: 5759585 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7747. Min Act: -0.1700
Data Index: 3824436 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9623. Min Range: -3.9623
Max Act: 3.7747. Min Act: -0.1700
Data Index: 2688694 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19