Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1258. Min Range: -9.1258
Max Act: 9.1258. Min Act: -0.1700
Data Index: 3784455 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1258. Min Range: -9.1258
Max Act: 9.0633. Min Act: -0.1700
Data Index: 5033136 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1258. Min Range: -9.1258
Max Act: 9.0008. Min Act: -0.1700
Data Index: 3249136 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.8758. Min Act: -0.1700
Data Index: 6270153 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.8758. Min Act: -0.1700
Data Index: 6331524 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.8133. Min Act: -0.1700
Data Index: 3801048 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.6258. Min Act: -0.1700
Data Index: 7392516 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.6258. Min Act: -0.1700
Data Index: 3452858 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 5467089 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 2191697 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 1619332 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 7837309 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 8749807 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5633. Min Act: -0.1700
Data Index: 278959 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5008. Min Act: -0.1700
Data Index: 1359003 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5008. Min Act: -0.1700
Data Index: 2562897 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.5008. Min Act: -0.1700
Data Index: 4239887 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.4383. Min Act: -0.1700
Data Index: 2793202 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.4383. Min Act: -0.1700
Data Index: 1891958 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1258. Min Range: -9.1258
Max Act: 8.3758. Min Act: -0.1700
Data Index: 6237911 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19