Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.0288. Min Range: -10.0288
Max Act: 10.0288. Min Act: -0.1700
Data Index: 1423765 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.7163. Min Act: -0.1700
Data Index: 3376712 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.7163. Min Act: -0.1700
Data Index: 6629740 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.6538. Min Act: -0.1700
Data Index: 4397554 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.6538. Min Act: -0.1700
Data Index: 7681791 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.5913. Min Act: -0.1700
Data Index: 5470463 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.5288. Min Act: -0.1700
Data Index: 7159465 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.5288. Min Act: -0.1700
Data Index: 1223210 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.5288. Min Act: -0.1700
Data Index: 1185220 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.4038. Min Act: -0.1700
Data Index: 7968086 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.4038. Min Act: -0.1700
Data Index: 8808668 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 4832330 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.4038. Min Act: -0.1700
Data Index: 5065678 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.3413. Min Act: -0.1700
Data Index: 5094958 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2163. Min Act: -0.1700
Data Index: 2749835 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 4812363 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 7002471 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 686820 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 144243 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0288. Min Range: -10.0288
Max Act: 9.3413. Min Act: -0.1700
Data Index: 850744 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19