Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.3768. Min Act: -0.1700
Data Index: 2968309 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.1893. Min Act: -0.1700
Data Index: 5118614 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.1268. Min Act: -0.1700
Data Index: 8058186 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.1268. Min Act: -0.1700
Data Index: 5174394 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.0956. Min Act: -0.1700
Data Index: 1538399 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.0643. Min Act: -0.1700
Data Index: 750732 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3768. Min Range: -7.3768
Max Act: 7.0018. Min Act: -0.1700
Data Index: 8420598 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.9706. Min Act: -0.1700
Data Index: 7348504 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.9393. Min Act: -0.1700
Data Index: 7426197 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.8456. Min Act: -0.1700
Data Index: 611357 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7831. Min Act: -0.1700
Data Index: 4337242 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7831. Min Act: -0.1700
Data Index: 841294 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7518. Min Act: -0.1700
Data Index: 8212625 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7206. Min Act: -0.1700
Data Index: 6568724 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7206. Min Act: -0.1700
Data Index: 4337243 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.7206. Min Act: -0.1700
Data Index: 8392190 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.6581. Min Act: -0.1700
Data Index: 2702603 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.6581. Min Act: -0.1700
Data Index: 6840220 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.6581. Min Act: -0.1700
Data Index: 2282758 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3768. Min Range: -7.3768
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5831474 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19