Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.8040. Min Act: -0.1700
Data Index: 4996885 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.8040. Min Act: -0.1700
Data Index: 7489285 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7954. Min Act: -0.1699
Data Index: 294412 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7781. Min Act: -0.1700
Data Index: 2999866 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7867. Min Act: -0.1700
Data Index: 1288422 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7867. Min Act: -0.1700
Data Index: 4461938 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7781. Min Act: -0.1700
Data Index: 1764203 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1700
Data Index: 2230720 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7781. Min Act: -0.1700
Data Index: 6352392 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 6795053 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1700
Data Index: 822710 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1700
Data Index: 4734638 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 4318642 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 448864 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 1783033 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1700
Data Index: 681343 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1699
Data Index: 7168533 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 798050 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7695. Min Act: -0.1700
Data Index: 6126410 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8040. Min Range: -1.8040
Max Act: 1.7609. Min Act: -0.1700
Data Index: 5146895 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19