Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.3833. Min Act: -0.1700
Data Index: 4380560 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.2896. Min Act: -0.1700
Data Index: 4915753 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.2896. Min Act: -0.1700
Data Index: 5577068 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.2271. Min Act: -0.1700
Data Index: 7363292 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.2271. Min Act: -0.1700
Data Index: 6286272 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1958. Min Act: -0.1700
Data Index: 5324724 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1646. Min Act: -0.1700
Data Index: 8510622 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.2271. Min Act: -0.1700
Data Index: 5875408 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 8026763 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1646. Min Act: -0.1700
Data Index: 3844128 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1646. Min Act: -0.1700
Data Index: 5528809 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1646. Min Act: -0.1700
Data Index: 8193232 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1958. Min Act: -0.1700
Data Index: 8715135 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1646. Min Act: -0.1699
Data Index: 1229318 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 4421647 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 2960595 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 2463172 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 8153059 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.1333. Min Act: -0.1700
Data Index: 8063105 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3833. Min Range: -5.3833
Max Act: 5.0708. Min Act: -0.1700
Data Index: 6290016 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19