Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.4069. Min Act: -0.1700
Data Index: 892401 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5876270 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.3131. Min Act: -0.1700
Data Index: 3634066 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.2819. Min Act: -0.1700
Data Index: 699429 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.2506. Min Act: -0.1700
Data Index: 5655328 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1881. Min Act: -0.1700
Data Index: 6288478 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1881. Min Act: -0.1700
Data Index: 3331319 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1569. Min Act: -0.1700
Data Index: 570306 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1569. Min Act: -0.1700
Data Index: 3964213 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1569. Min Act: -0.1700
Data Index: 4169060 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1256. Min Act: -0.1700
Data Index: 1072889 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.1256. Min Act: -0.1700
Data Index: 8756533 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0944. Min Act: -0.1700
Data Index: 1770943 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2516486 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0944. Min Act: -0.1700
Data Index: 6449971 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0944. Min Act: -0.1700
Data Index: 6854222 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0631. Min Act: -0.1700
Data Index: 818547 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0631. Min Act: -0.1700
Data Index: 4320520 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0631. Min Act: -0.1700
Data Index: 4740679 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4069. Min Range: -5.4069
Max Act: 5.0631. Min Act: -0.1700
Data Index: 1052342 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19