Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3669 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1115. Min Range: -4.1115
Max Act: 4.1115. Min Act: -0.1700
Data Index: 6194577 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1115. Min Range: -4.1115
Max Act: 4.0803. Min Act: -0.1700
Data Index: 1281685 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.9865. Min Act: -0.1700
Data Index: 6301792 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.8615. Min Act: -0.1700
Data Index: 6274246 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7989. Min Act: -0.1700
Data Index: 3967417 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7989. Min Act: -0.1700
Data Index: 7882557 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7676. Min Act: -0.1700
Data Index: 4395612 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7676. Min Act: -0.1700
Data Index: 1738838 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.8302. Min Act: -0.1700
Data Index: 5003031 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7989. Min Act: -0.1700
Data Index: 257099 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7989. Min Act: -0.1700
Data Index: 2358350 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7989. Min Act: -0.1700
Data Index: 6966094 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7676. Min Act: -0.1700
Data Index: 4525305 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5761224 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7364. Min Act: -0.1700
Data Index: 5731796 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7364. Min Act: -0.1700
Data Index: 5997165 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5975012 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7364. Min Act: -0.1700
Data Index: 4444708 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7364. Min Act: -0.1700
Data Index: 3574760 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1115. Min Range: -4.1115
Max Act: 3.7364. Min Act: -0.1700
Data Index: 4481263 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19