Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7819. Min Act: -0.1700
Data Index: 5583528 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7387. Min Act: -0.1700
Data Index: 1703848 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7387. Min Act: -0.1700
Data Index: 3243956 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7128. Min Act: -0.1700
Data Index: 526962 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7301. Min Act: -0.1697
Data Index: 5160839 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7214. Min Act: -0.1700
Data Index: 2367483 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7041. Min Act: -0.1700
Data Index: 4314797 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7301. Min Act: -0.1700
Data Index: 2877743 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7041. Min Act: -0.1700
Data Index: 6649614 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6954. Min Act: -0.1700
Data Index: 3080137 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6954. Min Act: -0.1700
Data Index: 4293092 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7041. Min Act: -0.1700
Data Index: 3619455 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6954. Min Act: -0.1700
Data Index: 7167467 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.7041. Min Act: -0.1700
Data Index: 6319633 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6781. Min Act: -0.1700
Data Index: 535684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6868. Min Act: -0.1699
Data Index: 1055745 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6868. Min Act: -0.1700
Data Index: 6481800 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6954. Min Act: -0.1700
Data Index: 1308396 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6868. Min Act: -0.1700
Data Index: 8366467 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7819. Min Range: -1.7819
Max Act: 1.6781. Min Act: -0.1700
Data Index: 94404 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19