Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 588 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6963. Min Act: -0.1700
Data Index: 5521105 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6651. Min Act: -0.1700
Data Index: 3447295 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.7276. Min Act: -0.1700
Data Index: 878929 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.7276. Min Act: -0.1700
Data Index: 347231 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6026. Min Act: -0.1700
Data Index: 8131403 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7910405 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8418487 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7049345 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 825915 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6920103 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 1294633 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 8826217 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 350790 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 2170764 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5862698 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5429616 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 7423191 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4463. Min Act: -0.1700
Data Index: 4702743 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6105832 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4151. Min Act: -0.1700
Data Index: 2414687 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19