Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.5622. Min Act: -0.1700
Data Index: 2313903 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.3122. Min Act: -0.1700
Data Index: 1709977 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.3122. Min Act: -0.1700
Data Index: 2911574 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.3122. Min Act: -0.1700
Data Index: 3719566 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.1247. Min Act: -0.1700
Data Index: 5733045 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5622. Min Range: -9.5622
Max Act: 9.0622. Min Act: -0.1700
Data Index: 7306100 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.9372. Min Act: -0.1700
Data Index: 5286502 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.9372. Min Act: -0.1700
Data Index: 8784126 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.9997. Min Act: -0.1700
Data Index: 5241649 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 939220 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 5526647 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 5643602 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 5727236 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 7555546 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 6976637 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 2627874 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 6730745 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.6872. Min Act: -0.1700
Data Index: 284364 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 1236250 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5622. Min Range: -9.5622
Max Act: 8.6872. Min Act: -0.1700
Data Index: 5133989 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19