Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4317 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.9778. Min Act: -0.1700
Data Index: 5044877 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0403. Min Range: -9.0403
Max Act: 9.0403. Min Act: -0.1700
Data Index: 3189211 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0403. Min Range: -9.0403
Max Act: 9.0403. Min Act: -0.1699
Data Index: 5483822 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.9778. Min Act: -0.1700
Data Index: 162515 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.9153. Min Act: -0.1700
Data Index: 7056268 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.9153. Min Act: -0.1700
Data Index: 6182304 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7903. Min Act: -0.1700
Data Index: 2157577 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7903. Min Act: -0.1700
Data Index: 2429656 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7903. Min Act: -0.1700
Data Index: 3461739 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 7864899 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 207087 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 7315374 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 5168724 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.6653. Min Act: -0.1699
Data Index: 714737 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 4832686 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 6233030 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1542
Data Index: 6403015 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 8160408 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 8197046 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0403. Min Range: -9.0403
Max Act: 8.7278. Min Act: -0.1700
Data Index: 946540 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19