Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.7442. Min Act: -0.1700
Data Index: 1157642 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.7442. Min Act: -0.1700
Data Index: 3338626 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6963. Min Act: -0.1700
Data Index: 3158082 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6963. Min Act: -0.1700
Data Index: 8243013 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6803. Min Act: -0.1700
Data Index: 4831146 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6642. Min Act: -0.1700
Data Index: 8097477 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6803. Min Act: -0.1700
Data Index: 244689 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6642. Min Act: -0.1700
Data Index: 6540867 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6482. Min Act: -0.1700
Data Index: 2512582 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6482. Min Act: -0.1700
Data Index: 4487379 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6642. Min Act: -0.1700
Data Index: 282884 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6321. Min Act: -0.1699
Data Index: 4390342 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6642. Min Act: -0.1686
Data Index: 3071973 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6482. Min Act: -0.1700
Data Index: 6895647 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6321. Min Act: -0.1699
Data Index: 4554670 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6321. Min Act: -0.1699
Data Index: 3515313 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6321. Min Act: -0.1700
Data Index: 7268136 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6161. Min Act: -0.1700
Data Index: 3970527 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6161. Min Act: -0.1700
Data Index: 3609807 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7442. Min Range: -2.7442
Max Act: 2.6161. Min Act: -0.1700
Data Index: 1014520 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19