Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5428 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6487. Min Act: -0.1700
Data Index: 8696534 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6487. Min Act: -0.1700
Data Index: 6138024 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6487. Min Act: -0.1700
Data Index: 7355610 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6313. Min Act: -0.1700
Data Index: 5728888 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6138. Min Act: -0.1700
Data Index: 2604075 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6138. Min Act: -0.1700
Data Index: 3758778 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6138. Min Act: -0.1700
Data Index: 3368266 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6138. Min Act: -0.1700
Data Index: 5985800 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.6138. Min Act: -0.1700
Data Index: 7569909 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5964. Min Act: -0.1700
Data Index: 3159743 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5964. Min Act: -0.1700
Data Index: 7770013 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5964. Min Act: -0.1700
Data Index: 8363051 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5789. Min Act: -0.1700
Data Index: 4055830 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5964. Min Act: -0.1700
Data Index: 914277 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5789. Min Act: -0.1700
Data Index: 6265308 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5964. Min Act: -0.1700
Data Index: 1939630 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5614. Min Act: -0.1700
Data Index: 890169 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5614. Min Act: -0.1700
Data Index: 5718483 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5614. Min Act: -0.1700
Data Index: 134940 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6487. Min Range: -1.6487
Max Act: 1.5614. Min Act: -0.1700
Data Index: 5970283 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19