Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2141 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9822. Min Act: -0.1700
Data Index: 6820755 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0138. Min Range: -3.0138
Max Act: 3.0138. Min Act: -0.1700
Data Index: 4706287 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9980. Min Act: -0.1700
Data Index: 4952903 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9348. Min Act: -0.1700
Data Index: 5620423 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9348. Min Act: -0.1700
Data Index: 3813603 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9348. Min Act: -0.1700
Data Index: 1703707 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9348. Min Act: -0.1700
Data Index: 3749640 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8872. Min Act: -0.1700
Data Index: 4506803 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9348. Min Act: -0.1700
Data Index: 2991301 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8713. Min Act: -0.1700
Data Index: 6268743 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8872. Min Act: -0.1700
Data Index: 6880037 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.9031. Min Act: -0.1700
Data Index: 7455107 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8713. Min Act: -0.1700
Data Index: 7974279 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8713. Min Act: -0.1700
Data Index: 1239626 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8554. Min Act: -0.1700
Data Index: 8827467 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8396. Min Act: -0.1700
Data Index: 3634274 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8396. Min Act: -0.1700
Data Index: 2560611 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8554. Min Act: -0.1700
Data Index: 3662429 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8554. Min Act: -0.1700
Data Index: 4057941 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0138. Min Range: -3.0138
Max Act: 2.8713. Min Act: -0.1700
Data Index: 7395936 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19