Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.1438. Min Act: -0.1700
Data Index: 3469276 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.1281. Min Act: -0.1700
Data Index: 3576974 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0808. Min Act: -0.1700
Data Index: 2276597 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0650. Min Act: -0.1700
Data Index: 3444611 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0493. Min Act: -0.1700
Data Index: 5013606 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0335. Min Act: -0.1700
Data Index: 7196734 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0335. Min Act: -0.1700
Data Index: 5711596 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0019. Min Act: -0.1700
Data Index: 4017665 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0019. Min Act: -0.1700
Data Index: 6855142 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1438. Min Range: -3.1438
Max Act: 3.0177. Min Act: -0.1700
Data Index: 3079030 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9861. Min Act: -0.1700
Data Index: 1675864 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9861. Min Act: -0.1700
Data Index: 8674095 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9703. Min Act: -0.1700
Data Index: 8267179 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9544. Min Act: -0.1700
Data Index: 4753252 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9703. Min Act: -0.1700
Data Index: 6965754 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9544. Min Act: -0.1700
Data Index: 5813990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9544. Min Act: -0.1700
Data Index: 5459821 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9544. Min Act: -0.1700
Data Index: 1173420 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9228. Min Act: -0.1700
Data Index: 5667338 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1438. Min Range: -3.1438
Max Act: 2.9386. Min Act: -0.1700
Data Index: 5813989 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19