Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4904. Min Range: -7.4904
Max Act: 7.4904. Min Act: -0.1700
Data Index: 7346060 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4904. Min Range: -7.4904
Max Act: 7.2716. Min Act: -0.1700
Data Index: 4499701 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4904. Min Range: -7.4904
Max Act: 7.1779. Min Act: -0.1700
Data Index: 2286 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9904. Min Act: -0.1700
Data Index: 6175479 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9904. Min Act: -0.1700
Data Index: 6138646 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9591. Min Act: -0.1700
Data Index: 6808917 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9591. Min Act: -0.1700
Data Index: 4826198 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9279. Min Act: -0.1700
Data Index: 2954355 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9279. Min Act: -0.1700
Data Index: 7293149 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9279. Min Act: -0.1700
Data Index: 7851545 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.9279. Min Act: -0.1700
Data Index: 4559326 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8654. Min Act: -0.1700
Data Index: 6689943 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8341. Min Act: -0.1700
Data Index: 7702356 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8029. Min Act: -0.1700
Data Index: 1838357 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8341. Min Act: -0.1700
Data Index: 8813618 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8341. Min Act: -0.1700
Data Index: 8656162 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8029. Min Act: -0.1700
Data Index: 8313672 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.7716. Min Act: -0.1700
Data Index: 5656489 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.7716. Min Act: -0.1700
Data Index: 5910939 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4904. Min Range: -7.4904
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4356924 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19