Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 1221391 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.9774. Min Act: -0.1700
Data Index: 4193532 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.9149. Min Act: -0.1700
Data Index: 6402748 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.8211. Min Act: -0.1700
Data Index: 169818 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.7899. Min Act: -0.1700
Data Index: 1384771 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.7899. Min Act: -0.1700
Data Index: 6234116 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.7274. Min Act: -0.1700
Data Index: 119285 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.7274. Min Act: -0.1700
Data Index: 5994500 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 2974953 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 393309 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 4088175 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1258207 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 6372134 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 3905766 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 1930863 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 795312 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 6436700 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 3937425 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1918198 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2586. Min Range: -5.2586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 2334769 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19