Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.5512. Min Act: -0.1700
Data Index: 5941531 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.4262. Min Act: -0.1700
Data Index: 1595056 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.4262. Min Act: -0.1700
Data Index: 4694305 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.3950. Min Act: -0.1700
Data Index: 3728116 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.3637. Min Act: -0.1700
Data Index: 2540250 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.3325. Min Act: -0.1700
Data Index: 943225 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.3012. Min Act: -0.1700
Data Index: 1515827 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.2700. Min Act: -0.1700
Data Index: 6711497 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.3012. Min Act: -0.1700
Data Index: 2487004 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.2387. Min Act: -0.1700
Data Index: 6366828 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.2387. Min Act: -0.1700
Data Index: 8760366 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1762. Min Act: -0.1700
Data Index: 8716067 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.2075. Min Act: -0.1700
Data Index: 5666431 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1762. Min Act: -0.1700
Data Index: 8276284 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.2075. Min Act: -0.1700
Data Index: 4648347 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1762. Min Act: -0.1700
Data Index: 2942050 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1450. Min Act: -0.1700
Data Index: 3307242 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1137. Min Act: -0.1700
Data Index: 5540061 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1137. Min Act: -0.1700
Data Index: 6716220 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5512. Min Range: -5.5512
Max Act: 5.1137. Min Act: -0.1700
Data Index: 8629097 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19