Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.4612. Min Act: -0.1700
Data Index: 5479794 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.3362. Min Act: -0.1700
Data Index: 5479795 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.2737. Min Act: -0.1700
Data Index: 6693154 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.2425. Min Act: -0.1700
Data Index: 2575538 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6765121 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1800. Min Act: -0.1700
Data Index: 8138773 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1800. Min Act: -0.1700
Data Index: 1407005 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1487. Min Act: -0.1700
Data Index: 224396 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1487. Min Act: -0.1700
Data Index: 5680399 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1487. Min Act: -0.1700
Data Index: 8581964 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 6735957 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1175. Min Act: -0.1700
Data Index: 8008531 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.1175. Min Act: -0.1700
Data Index: 8626332 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3323297 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3487931 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 6431755 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 6254455 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0862. Min Act: -0.1700
Data Index: 4304300 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0550. Min Act: -0.1700
Data Index: 1346460 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4612. Min Range: -5.4612
Max Act: 5.0237. Min Act: -0.1700
Data Index: 7524950 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19