Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.7469. Min Act: -0.1700
Data Index: 4771453 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.5865. Min Act: -0.1700
Data Index: 4999850 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.5865. Min Act: -0.1700
Data Index: 7466431 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.5704. Min Act: -0.1700
Data Index: 2766282 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.5381. Min Act: -0.1700
Data Index: 2524901 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4733. Min Act: -0.1700
Data Index: 578990 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.5058. Min Act: -0.1700
Data Index: 87976 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4733. Min Act: -0.1700
Data Index: 3740434 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4733. Min Act: -0.1700
Data Index: 283740 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4571. Min Act: -0.1700
Data Index: 1999998 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4408. Min Act: -0.1700
Data Index: 3491615 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4408. Min Act: -0.1700
Data Index: 2549712 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4246. Min Act: -0.1700
Data Index: 4831207 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4083. Min Act: -0.1700
Data Index: 7778088 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4246. Min Act: -0.1700
Data Index: 5555703 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4083. Min Act: -0.1700
Data Index: 2202498 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.3919. Min Act: -0.1700
Data Index: 5330013 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.4083. Min Act: -0.1700
Data Index: 3277647 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.3919. Min Act: -0.1700
Data Index: 2442372 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7469. Min Range: -2.7469
Max Act: 2.3756. Min Act: -0.1700
Data Index: 2384434 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19