Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.5443. Min Act: -0.1700
Data Index: 7816059 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.4505. Min Act: -0.1700
Data Index: 5784323 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.4193. Min Act: -0.1700
Data Index: 3482062 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.3568. Min Act: -0.1700
Data Index: 2079871 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.3568. Min Act: -0.1700
Data Index: 1688719 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.3568. Min Act: -0.1700
Data Index: 5002010 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.3255. Min Act: -0.1700
Data Index: 8353766 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2943. Min Act: -0.1700
Data Index: 4602313 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2943. Min Act: -0.1700
Data Index: 8819838 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2630. Min Act: -0.1700
Data Index: 5595238 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2630. Min Act: -0.1700
Data Index: 4868380 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2630. Min Act: -0.1700
Data Index: 7070244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2630. Min Act: -0.1700
Data Index: 5800778 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2943. Min Act: -0.1700
Data Index: 5292828 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2317. Min Act: -0.1700
Data Index: 6877411 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.1692. Min Act: -0.1700
Data Index: 4681421 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2005. Min Act: -0.1700
Data Index: 4804681 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.1692. Min Act: -0.1700
Data Index: 8452243 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.2005. Min Act: -0.1700
Data Index: 5573236 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5443. Min Range: -4.5443
Max Act: 4.1692. Min Act: -0.1700
Data Index: 7403418 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19