Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3851 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.2980. Min Act: -0.1700
Data Index: 8469837 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.1730. Min Act: -0.1700
Data Index: 1260604 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.1418. Min Act: -0.1700
Data Index: 5471780 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.1418. Min Act: -0.1700
Data Index: 2243081 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0480. Min Act: -0.1700
Data Index: 8264002 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0167. Min Act: -0.1700
Data Index: 2300195 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9542. Min Act: -0.1700
Data Index: 2498053 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9542. Min Act: -0.1700
Data Index: 5745858 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 5509376 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 8140461 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8917. Min Act: -0.1700
Data Index: 1072686 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8917. Min Act: -0.1700
Data Index: 4555564 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 5717375 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 5996711 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 5996719 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8448. Min Act: -0.1700
Data Index: 1511058 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8448. Min Act: -0.1700
Data Index: 7111751 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8448. Min Act: -0.1700
Data Index: 7144589 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8448. Min Act: -0.1700
Data Index: 1888679 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8292. Min Act: -0.1700
Data Index: 502788 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19