Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.6058. Min Act: -0.1700
Data Index: 1063647 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.4496. Min Act: -0.1700
Data Index: 6038421 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.3246. Min Act: -0.1700
Data Index: 1879598 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1996. Min Act: -0.1700
Data Index: 1427368 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1996. Min Act: -0.1700
Data Index: 7164429 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1996. Min Act: -0.1700
Data Index: 6301430 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1996. Min Act: -0.1700
Data Index: 1424214 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1683. Min Act: -0.1700
Data Index: 8069819 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.1371. Min Act: -0.1700
Data Index: 6071378 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0746. Min Act: -0.1700
Data Index: 3720864 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0746. Min Act: -0.1700
Data Index: 5447783 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0746. Min Act: -0.1700
Data Index: 2983747 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 5577090 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 854479 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 1764891 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 1028018 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 1372011 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0121. Min Act: -0.1700
Data Index: 4788883 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0121. Min Act: -0.1700
Data Index: 8245961 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6058. Min Range: -7.6058
Max Act: 7.0121. Min Act: -0.1700
Data Index: 1809875 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19