Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1197. Min Range: -4.1197
Max Act: 4.0571. Min Act: -0.1700
Data Index: 4737673 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1197. Min Range: -4.1197
Max Act: 4.1197. Min Act: -0.1700
Data Index: 894084 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1197. Min Range: -4.1197
Max Act: 4.0259. Min Act: -0.1699
Data Index: 4999877 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1197. Min Range: -4.1197
Max Act: 4.0259. Min Act: -0.1697
Data Index: 56101 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8696. Min Act: -0.1700
Data Index: 3828476 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.9321. Min Act: -0.1700
Data Index: 1306039 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.9634. Min Act: -0.1700
Data Index: 5435439 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.9008. Min Act: -0.1700
Data Index: 957709 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8696. Min Act: -0.1700
Data Index: 988219 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.9008. Min Act: -0.1700
Data Index: 581938 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8383. Min Act: -0.1700
Data Index: 6519161 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8070. Min Act: -0.1700
Data Index: 4384344 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8383. Min Act: -0.1700
Data Index: 7265300 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.7601. Min Act: -0.1700
Data Index: 6245326 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.7601. Min Act: -0.1700
Data Index: 3866986 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.8070. Min Act: -0.1700
Data Index: 8062512 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.6819. Min Act: -0.1700
Data Index: 3680053 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.6819. Min Act: -0.1700
Data Index: 3730668 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.7132. Min Act: -0.1700
Data Index: 6051369 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1197. Min Range: -4.1197
Max Act: 3.7288. Min Act: -0.1700
Data Index: 5452501 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19