Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.7688. Min Act: -0.1700
Data Index: 3655491 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.7688. Min Act: -0.1700
Data Index: 6208236 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.7688. Min Act: -0.1700
Data Index: 2933396 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.7063. Min Act: -0.1700
Data Index: 6814996 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.6438. Min Act: -0.1700
Data Index: 5373905 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.4563. Min Act: -0.1700
Data Index: 1893639 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.3938. Min Act: -0.1700
Data Index: 58835 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.3938. Min Act: -0.1700
Data Index: 6024659 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.3313. Min Act: -0.1700
Data Index: 8051435 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.2688. Min Act: -0.1700
Data Index: 2933403 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.2375. Min Act: -0.1700
Data Index: 8051434 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.2063. Min Act: -0.1700
Data Index: 3559380 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1750. Min Act: -0.1700
Data Index: 3350126 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1438. Min Act: -0.1700
Data Index: 2944740 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1438. Min Act: -0.1700
Data Index: 2337458 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1125. Min Act: -0.1700
Data Index: 1746442 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1125. Min Act: -0.1700
Data Index: 7934452 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.1125. Min Act: -0.1700
Data Index: 8723261 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.0188. Min Act: -0.1700
Data Index: 5517074 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7688. Min Range: -7.7688
Max Act: 7.0188. Min Act: -0.1700
Data Index: 3749363 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19