Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2893. Min Range: -8.2893
Max Act: 8.2893. Min Act: -0.1700
Data Index: 7537855 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.7893. Min Act: -0.1700
Data Index: 379396 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.6643. Min Act: -0.1700
Data Index: 7671163 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.6643. Min Act: -0.1700
Data Index: 7537850 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.3518. Min Act: -0.1700
Data Index: 8239908 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.3205. Min Act: -0.1700
Data Index: 1249437 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.2580. Min Act: -0.1700
Data Index: 3375058 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.1955. Min Act: -0.1700
Data Index: 3472564 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.1955. Min Act: -0.1700
Data Index: 6354152 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.2268. Min Act: -0.1700
Data Index: 4386213 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.0705. Min Act: -0.1700
Data Index: 5139085 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.0393. Min Act: -0.1700
Data Index: 7727775 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.0393. Min Act: -0.1700
Data Index: 3066481 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.0080. Min Act: -0.1700
Data Index: 6860957 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2893. Min Range: -8.2893
Max Act: 7.0080. Min Act: -0.1700
Data Index: 2890932 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2893. Min Range: -8.2893
Max Act: 6.9768. Min Act: -0.1699
Data Index: 3066486 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2893. Min Range: -8.2893
Max Act: 6.8830. Min Act: -0.1700
Data Index: 6372456 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2893. Min Range: -8.2893
Max Act: 6.8830. Min Act: -0.1700
Data Index: 2378098 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2893. Min Range: -8.2893
Max Act: 6.8830. Min Act: -0.1700
Data Index: 8260350 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2893. Min Range: -8.2893
Max Act: 6.9143. Min Act: -0.1700
Data Index: 7107470 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19