Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0820. Min Range: -6.0820
Max Act: 6.0820. Min Act: -0.1700
Data Index: 7706663 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.6757. Min Act: -0.1700
Data Index: 5631254 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.6445. Min Act: -0.1700
Data Index: 4463251 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.5820. Min Act: -0.1700
Data Index: 7272992 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.4570. Min Act: -0.1700
Data Index: 2052857 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.4882. Min Act: -0.1700
Data Index: 426158 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.4257. Min Act: -0.1700
Data Index: 3905418 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.4257. Min Act: -0.1700
Data Index: 7692399 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.4257. Min Act: -0.1700
Data Index: 8392849 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 4036311 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3632. Min Act: -0.1700
Data Index: 3541568 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 7324725 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 6557024 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 4037069 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 6905642 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 6482746 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 2347725 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 3041453 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.2382. Min Act: -0.1700
Data Index: 5277117 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0820. Min Range: -6.0820
Max Act: 5.2695. Min Act: -0.1700
Data Index: 2894039 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19