Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4542. Min Range: -9.4542
Max Act: 9.4542. Min Act: -0.1700
Data Index: 7782966 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4542. Min Range: -9.4542
Max Act: 9.1417. Min Act: -0.1700
Data Index: 3258053 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4542. Min Range: -9.4542
Max Act: 9.0167. Min Act: -0.1700
Data Index: 530606 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4542. Min Range: -9.4542
Max Act: 9.0167. Min Act: -0.1700
Data Index: 8202550 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4542. Min Range: -9.4542
Max Act: 9.0167. Min Act: -0.1700
Data Index: 1555184 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.9542. Min Act: -0.1700
Data Index: 5592668 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.9542. Min Act: -0.1700
Data Index: 2973252 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.9542. Min Act: -0.1700
Data Index: 6038204 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.9542. Min Act: -0.1700
Data Index: 4951847 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.8917. Min Act: -0.1700
Data Index: 2016012 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.8292. Min Act: -0.1700
Data Index: 5359037 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.8292. Min Act: -0.1700
Data Index: 4722662 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.8292. Min Act: -0.1700
Data Index: 1375850 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7667. Min Act: -0.1700
Data Index: 857202 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7667. Min Act: -0.1700
Data Index: 38884 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7667. Min Act: -0.1700
Data Index: 222158 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7042. Min Act: -0.1700
Data Index: 7087811 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7042. Min Act: -0.1700
Data Index: 4885613 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7042. Min Act: -0.1700
Data Index: 3191739 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4542. Min Range: -9.4542
Max Act: 8.7042. Min Act: -0.1700
Data Index: 4585389 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19