Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2620. Min Range: -6.2620
Max Act: 6.2620. Min Act: -0.1700
Data Index: 3620106 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2620. Min Range: -6.2620
Max Act: 6.0120. Min Act: -0.1700
Data Index: 131176 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2620. Min Range: -6.2620
Max Act: 6.0120. Min Act: -0.1700
Data Index: 4223327 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.9808. Min Act: -0.1700
Data Index: 3272362 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2620. Min Range: -6.2620
Max Act: 6.0120. Min Act: -0.1700
Data Index: 2765724 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.9808. Min Act: -0.1700
Data Index: 4765912 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1382590 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.8870. Min Act: -0.1700
Data Index: 2762602 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.8870. Min Act: -0.1700
Data Index: 5126934 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.8870. Min Act: -0.1700
Data Index: 6398213 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.8245. Min Act: -0.1700
Data Index: 4781846 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.8245. Min Act: -0.1700
Data Index: 7319650 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7933. Min Act: -0.1700
Data Index: 3155719 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7933. Min Act: -0.1700
Data Index: 8523907 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7933. Min Act: -0.1700
Data Index: 528759 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7620. Min Act: -0.1700
Data Index: 7520438 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7620. Min Act: -0.1700
Data Index: 3823508 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7620. Min Act: -0.1700
Data Index: 7197271 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7308. Min Act: -0.1700
Data Index: 2865682 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2620. Min Range: -6.2620
Max Act: 5.7308. Min Act: -0.1700
Data Index: 463621 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19