Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2169. Min Range: -5.2169
Max Act: 5.2169. Min Act: -0.1700
Data Index: 1900194 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2169. Min Range: -5.2169
Max Act: 5.0294. Min Act: -0.1700
Data Index: 3955828 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9982. Min Act: -0.1700
Data Index: 2571735 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9982. Min Act: -0.1700
Data Index: 237098 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9982. Min Act: -0.1700
Data Index: 237099 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9669. Min Act: -0.1700
Data Index: 4885238 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9669. Min Act: -0.1700
Data Index: 3078581 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9669. Min Act: -0.1700
Data Index: 692807 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9357. Min Act: -0.1700
Data Index: 1544602 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9357. Min Act: -0.1700
Data Index: 4297503 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8622477 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9357. Min Act: -0.1700
Data Index: 1377017 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.9044. Min Act: -0.1700
Data Index: 5554489 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8732. Min Act: -0.1700
Data Index: 6606237 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8419. Min Act: -0.1700
Data Index: 3680886 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8419. Min Act: -0.1700
Data Index: 2139905 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8419. Min Act: -0.1700
Data Index: 2130204 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.7794. Min Act: -0.1700
Data Index: 3897950 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8107. Min Act: -0.1700
Data Index: 7100116 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2169. Min Range: -5.2169
Max Act: 4.8107. Min Act: -0.1700
Data Index: 2993730 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19