Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.5177. Min Act: -0.1700
Data Index: 1716296 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.4552. Min Act: -0.1700
Data Index: 6148560 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.2990. Min Act: -0.1698
Data Index: 4670704 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.2365. Min Act: -0.1700
Data Index: 7151535 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.1427. Min Act: -0.1700
Data Index: 1966065 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5177. Min Range: -6.5177
Max Act: 6.0802. Min Act: -0.1700
Data Index: 2479261 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9865. Min Act: -0.1700
Data Index: 6615022 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9865. Min Act: -0.1700
Data Index: 4927537 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2412695 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1217024 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9552. Min Act: -0.1700
Data Index: 7110743 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.9552. Min Act: -0.1700
Data Index: 7924148 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8927. Min Act: -0.1700
Data Index: 7248395 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8615. Min Act: -0.1700
Data Index: 7230937 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8615. Min Act: -0.1700
Data Index: 383077 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5918826 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2255547 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2189482 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8615. Min Act: -0.1700
Data Index: 6615021 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5177. Min Range: -6.5177
Max Act: 5.8927. Min Act: -0.1700
Data Index: 929316 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19