Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3034. Min Range: -5.3034
Max Act: 5.3034. Min Act: -0.1700
Data Index: 3671242 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3034. Min Range: -5.3034
Max Act: 5.2409. Min Act: -0.1700
Data Index: 7889739 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3034. Min Range: -5.3034
Max Act: 5.1784. Min Act: -0.1700
Data Index: 2998760 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3034. Min Range: -5.3034
Max Act: 5.0847. Min Act: -0.1700
Data Index: 925429 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3034. Min Range: -5.3034
Max Act: 5.0222. Min Act: -0.1700
Data Index: 4645653 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.9284. Min Act: -0.1700
Data Index: 6436921 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.9284. Min Act: -0.1700
Data Index: 6548624 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8972. Min Act: -0.1700
Data Index: 7596200 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8972. Min Act: -0.1700
Data Index: 2699556 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8659. Min Act: -0.1700
Data Index: 6411710 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8659. Min Act: -0.1700
Data Index: 2115793 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8659. Min Act: -0.1700
Data Index: 1987849 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.8034. Min Act: -0.1700
Data Index: 1706652 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.7097. Min Act: -0.1700
Data Index: 8433499 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.7097. Min Act: -0.1700
Data Index: 216452 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.6784. Min Act: -0.1700
Data Index: 8387796 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.7097. Min Act: -0.1700
Data Index: 5187721 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.6472. Min Act: -0.1700
Data Index: 4689506 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.6472. Min Act: -0.1700
Data Index: 1864255 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3034. Min Range: -5.3034
Max Act: 4.6159. Min Act: -0.1700
Data Index: 4870900 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19