Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5662. Min Act: -0.1700
Data Index: 5817388 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5037. Min Act: -0.1700
Data Index: 1713461 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3475. Min Act: -0.1700
Data Index: 7533399 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2225. Min Act: -0.1700
Data Index: 4550939 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0662. Min Act: -0.1700
Data Index: 2096623 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 1738022 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 6728420 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0037. Min Act: -0.1700
Data Index: 1013105 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 901853 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 7052197 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 7474302 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 960415 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 4389719 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 4169651 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 7766485 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 1184278 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9100. Min Act: -0.1700
Data Index: 366595 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2596058 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9100. Min Act: -0.1700
Data Index: 7004246 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9100. Min Act: -0.1700
Data Index: 4418192 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19