Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5242 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0612. Min Range: -5.0612
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4728130 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2194723 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2267497 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8425. Min Act: -0.1700
Data Index: 1301084 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8425. Min Act: -0.1700
Data Index: 4150545 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.8112. Min Act: -0.1700
Data Index: 5529195 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7487. Min Act: -0.1700
Data Index: 8317767 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7487. Min Act: -0.1700
Data Index: 8756322 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7175. Min Act: -0.1700
Data Index: 7853995 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7487. Min Act: -0.1700
Data Index: 6122314 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7175. Min Act: -0.1700
Data Index: 4842530 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7175. Min Act: -0.1700
Data Index: 7125192 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.7175. Min Act: -0.1700
Data Index: 2953905 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6862. Min Act: -0.1700
Data Index: 5536599 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6862. Min Act: -0.1700
Data Index: 457544 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6550. Min Act: -0.1700
Data Index: 5835919 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8026611 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6550. Min Act: -0.1700
Data Index: 998282 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6550. Min Act: -0.1700
Data Index: 5599316 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0612. Min Range: -5.0612
Max Act: 4.6550. Min Act: -0.1700
Data Index: 3016523 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19