Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 943 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1809. Min Range: -7.1809
Max Act: 7.1809. Min Act: -0.1700
Data Index: 833168 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1809. Min Range: -7.1809
Max Act: 7.1809. Min Act: -0.1700
Data Index: 3803483 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1809. Min Range: -7.1809
Max Act: 7.0559. Min Act: -0.1700
Data Index: 6496892 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1809. Min Range: -7.1809
Max Act: 7.0247. Min Act: -0.1700
Data Index: 946112 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1809. Min Range: -7.1809
Max Act: 7.0247. Min Act: -0.1700
Data Index: 7420148 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.9934. Min Act: -0.1700
Data Index: 1188030 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.8997. Min Act: -0.1700
Data Index: 2651901 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.8997. Min Act: -0.1700
Data Index: 5401716 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.8059. Min Act: -0.1700
Data Index: 7034056 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.7747. Min Act: -0.1700
Data Index: 7380669 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.7434. Min Act: -0.1700
Data Index: 4983290 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.7122. Min Act: -0.1700
Data Index: 3176187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.7122. Min Act: -0.1700
Data Index: 8412428 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.6809. Min Act: -0.1700
Data Index: 3155842 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.7122. Min Act: -0.1700
Data Index: 6626648 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.6809. Min Act: -0.1700
Data Index: 4446231 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.6184. Min Act: -0.1700
Data Index: 949320 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.5872. Min Act: -0.1700
Data Index: 8084795 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.5872. Min Act: -0.1700
Data Index: 8220756 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1809. Min Range: -7.1809
Max Act: 6.5559. Min Act: -0.1700
Data Index: 4306619 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19