Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.1642. Min Act: -0.1700
Data Index: 2507193 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.1329. Min Act: -0.1700
Data Index: 4316821 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0704. Min Act: -0.1700
Data Index: 2679082 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0704. Min Act: -0.1700
Data Index: 1355632 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 1399261 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 8479363 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 7791092 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1642. Min Range: -6.1642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 1891573 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.9454. Min Act: -0.1700
Data Index: 4128096 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.9767. Min Act: -0.1700
Data Index: 6957731 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.9454. Min Act: -0.1700
Data Index: 3188 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 1142178 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.9142. Min Act: -0.1700
Data Index: 7436172 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.9142. Min Act: -0.1700
Data Index: 208806 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 7655648 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 2224990 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8517. Min Act: -0.1700
Data Index: 3022664 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 242634 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 4241140 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1642. Min Range: -6.1642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 8631599 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19