Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.8944. Min Act: -0.1700
Data Index: 7654180 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.8631. Min Act: -0.1700
Data Index: 6676568 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.7381. Min Act: -0.1700
Data Index: 7172064 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6756. Min Act: -0.1700
Data Index: 1045874 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6444. Min Act: -0.1700
Data Index: 742357 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6444. Min Act: -0.1700
Data Index: 4671918 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6444. Min Act: -0.1700
Data Index: 3873211 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6131. Min Act: -0.1700
Data Index: 1892909 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6444. Min Act: -0.1700
Data Index: 1858071 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.6131. Min Act: -0.1700
Data Index: 3124771 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5819. Min Act: -0.1700
Data Index: 2980668 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5506. Min Act: -0.1700
Data Index: 2546193 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5506. Min Act: -0.1700
Data Index: 2816162 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5194. Min Act: -0.1700
Data Index: 759497 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5194. Min Act: -0.1700
Data Index: 121744 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7022030 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.4881. Min Act: -0.1700
Data Index: 7298778 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.4881. Min Act: -0.1700
Data Index: 7682136 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.4881. Min Act: -0.1700
Data Index: 1841675 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8944. Min Range: -4.8944
Max Act: 4.4881. Min Act: -0.1700
Data Index: 7743585 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19