Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.3435. Min Act: -0.1700
Data Index: 1767245 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.3435. Min Act: -0.1700
Data Index: 3023809 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.1560. Min Act: -0.1700
Data Index: 4755127 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.1560. Min Act: -0.1700
Data Index: 4410540 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.1872. Min Act: -0.1700
Data Index: 5593302 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.1560. Min Act: -0.1700
Data Index: 162650 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.0935. Min Act: -0.1700
Data Index: 4417997 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.0622. Min Act: -0.1700
Data Index: 2226481 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.0310. Min Act: -0.1700
Data Index: 361244 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.0310. Min Act: -0.1700
Data Index: 797739 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3435. Min Range: -7.3435
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1393039 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9685. Min Act: -0.1700
Data Index: 3531269 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9685. Min Act: -0.1700
Data Index: 7995469 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9685. Min Act: -0.1700
Data Index: 5884374 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4116050 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9060. Min Act: -0.1700
Data Index: 7967241 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4027211 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9060. Min Act: -0.1700
Data Index: 8419115 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4503001 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3435. Min Range: -7.3435
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4075156 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19