Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6320 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.5056. Min Act: -0.1700
Data Index: 3176310 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.3806. Min Act: -0.1700
Data Index: 6105099 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.2556. Min Act: -0.1700
Data Index: 8641424 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.2556. Min Act: -0.1700
Data Index: 599083 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.1306. Min Act: -0.1700
Data Index: 7492728 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.1306. Min Act: -0.1700
Data Index: 2762759 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 8126813 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 5312077 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 2331970 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 5608214 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 6929117 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.5056. Min Range: -16.5056
Max Act: 16.0056. Min Act: -0.1700
Data Index: 5641544 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.9431. Min Act: -0.1700
Data Index: 3251487 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.9431. Min Act: -0.1700
Data Index: 4400759 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.8806. Min Act: -0.1700
Data Index: 89323 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.9431. Min Act: -0.1700
Data Index: 1507832 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.9431. Min Act: -0.1700
Data Index: 7967176 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.9431. Min Act: -0.1700
Data Index: 2669799 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.8181. Min Act: -0.1700
Data Index: 6992264 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.5056. Min Range: -16.5056
Max Act: 15.8181. Min Act: -0.1700
Data Index: 2862560 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19