Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.3636. Min Act: -0.1700
Data Index: 1196563 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.3011. Min Act: -0.1700
Data Index: 5508836 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.1761. Min Act: -0.1700
Data Index: 8739463 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.1449. Min Act: -0.1700
Data Index: 5512999 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.9886. Min Act: -0.1700
Data Index: 7491208 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.0199. Min Act: -0.1700
Data Index: 1495924 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3636. Min Range: -6.3636
Max Act: 6.0199. Min Act: -0.1700
Data Index: 2998300 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.7074. Min Act: -0.1700
Data Index: 2841428 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.7386. Min Act: -0.1700
Data Index: 991455 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.7074. Min Act: -0.1700
Data Index: 5562661 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.6761. Min Act: -0.1700
Data Index: 2980292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.5824. Min Act: -0.1700
Data Index: 2438556 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.5824. Min Act: -0.1700
Data Index: 6131386 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.4886. Min Act: -0.1700
Data Index: 3269455 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.4261. Min Act: -0.1700
Data Index: 5642072 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.3636. Min Act: -0.1700
Data Index: 4579681 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.3949. Min Act: -0.1700
Data Index: 4722483 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.3949. Min Act: -0.1700
Data Index: 2406262 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.3324. Min Act: -0.1700
Data Index: 2984672 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3636. Min Range: -6.3636
Max Act: 5.3324. Min Act: -0.1700
Data Index: 4038268 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19