Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0307. Min Range: -4.0307
Max Act: 4.0307. Min Act: -0.1700
Data Index: 8478238 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.9057. Min Act: -0.1700
Data Index: 1222325 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8744. Min Act: -0.1700
Data Index: 8516178 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8432. Min Act: -0.1700
Data Index: 8623952 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8432. Min Act: -0.1700
Data Index: 4870817 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7963. Min Act: -0.1700
Data Index: 5353393 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7963. Min Act: -0.1700
Data Index: 4294145 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7493. Min Act: -0.1700
Data Index: 4233939 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7337. Min Act: -0.1700
Data Index: 1013830 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7024. Min Act: -0.1700
Data Index: 755165 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7181. Min Act: -0.1700
Data Index: 830979 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7024. Min Act: -0.1700
Data Index: 153153 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6711. Min Act: -0.1700
Data Index: 3340309 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6868. Min Act: -0.1700
Data Index: 8410175 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6555. Min Act: -0.1700
Data Index: 5369654 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6555. Min Act: -0.1700
Data Index: 5712349 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6555. Min Act: -0.1700
Data Index: 6527169 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6398. Min Act: -0.1700
Data Index: 4713193 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6242. Min Act: -0.1700
Data Index: 4030482 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6085. Min Act: -0.1700
Data Index: 750461 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19