Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.3163. Min Act: -0.1700
Data Index: 6874709 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 8096003 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.0662. Min Act: -0.1700
Data Index: 4008937 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.0350. Min Act: -0.1700
Data Index: 2622391 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.0037. Min Act: -0.1700
Data Index: 1760344 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.0037. Min Act: -0.1700
Data Index: 4464805 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9725. Min Act: -0.1700
Data Index: 3250386 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9725. Min Act: -0.1700
Data Index: 7557114 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9725. Min Act: -0.1700
Data Index: 663046 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9099. Min Act: -0.1700
Data Index: 3308060 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9412. Min Act: -0.1700
Data Index: 5221206 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9099. Min Act: -0.1700
Data Index: 644052 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9412. Min Act: -0.1700
Data Index: 29003 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9412. Min Act: -0.1700
Data Index: 7878189 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9412. Min Act: -0.1700
Data Index: 7778344 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9099. Min Act: -0.1700
Data Index: 7600445 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9099. Min Act: -0.1700
Data Index: 1678153 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.9099. Min Act: -0.1700
Data Index: 3660318 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.8787. Min Act: -0.1700
Data Index: 4764087 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3163. Min Range: -4.3163
Max Act: 3.8787. Min Act: -0.1700
Data Index: 6267529 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19