Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.4457. Min Act: -0.1700
Data Index: 3159126 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.2582. Min Act: -0.1700
Data Index: 315844 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.1957. Min Act: -0.1700
Data Index: 7675549 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.0707. Min Act: -0.1700
Data Index: 726738 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.0707. Min Act: -0.1700
Data Index: 1337559 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.0082. Min Act: -0.1700
Data Index: 589249 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 1277433 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 1348399 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 6758935 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4457. Min Range: -8.4457
Max Act: 8.0082. Min Act: -0.1700
Data Index: 123711 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 47101 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 874173 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 5957235 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8832. Min Act: -0.1700
Data Index: 2022984 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.9457. Min Act: -0.1700
Data Index: 8348122 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8832. Min Act: -0.1700
Data Index: 6050262 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8520. Min Act: -0.1700
Data Index: 6945048 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8207. Min Act: -0.1700
Data Index: 7497277 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8207. Min Act: -0.1700
Data Index: 4858319 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4457. Min Range: -8.4457
Max Act: 7.8520. Min Act: -0.1700
Data Index: 8177578 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19