Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5253 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 2497947 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.2521. Min Act: -0.1700
Data Index: 1332989 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.1896. Min Act: -0.1700
Data Index: 2825668 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.1271. Min Act: -0.1700
Data Index: 2361465 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.1271. Min Act: -0.1700
Data Index: 6814613 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0646. Min Act: -0.1700
Data Index: 6520216 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0646. Min Act: -0.1700
Data Index: 7725966 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0646. Min Act: -0.1700
Data Index: 7236910 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0021. Min Act: -0.1700
Data Index: 5926032 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0021. Min Act: -0.1700
Data Index: 857828 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2521. Min Range: -7.2521
Max Act: 7.0021. Min Act: -0.1700
Data Index: 4080846 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9396. Min Act: -0.1700
Data Index: 7892546 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9708. Min Act: -0.1700
Data Index: 6113064 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9083. Min Act: -0.1700
Data Index: 72186 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9396. Min Act: -0.1700
Data Index: 6322221 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9083. Min Act: -0.1700
Data Index: 53088 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9083. Min Act: -0.1700
Data Index: 6217589 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.9083. Min Act: -0.1700
Data Index: 2878413 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.8771. Min Act: -0.1700
Data Index: 1932596 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2521. Min Range: -7.2521
Max Act: 6.8771. Min Act: -0.1700
Data Index: 6050810 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19