Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0492. Min Range: -5.0492
Max Act: 5.0492. Min Act: -0.1700
Data Index: 1719285 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0492. Min Range: -5.0492
Max Act: 5.0179. Min Act: -0.1700
Data Index: 3935918 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.9554. Min Act: -0.1700
Data Index: 7901735 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.8617. Min Act: -0.1700
Data Index: 1135405 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.8304. Min Act: -0.1700
Data Index: 2827315 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7679. Min Act: -0.1700
Data Index: 6665743 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7992. Min Act: -0.1700
Data Index: 1117027 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7367. Min Act: -0.1700
Data Index: 5022590 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 2015791 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 4038945 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 1497031 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 711906 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 3976465 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 1744716 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.6742. Min Act: -0.1700
Data Index: 5073171 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.7054. Min Act: -0.1700
Data Index: 4423409 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.6742. Min Act: -0.1700
Data Index: 2924877 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.6742. Min Act: -0.1700
Data Index: 416016 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.6429. Min Act: -0.1700
Data Index: 4950958 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0492. Min Range: -5.0492
Max Act: 4.6742. Min Act: -0.1700
Data Index: 6510693 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19