Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 549 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1206. Min Range: -4.1206
Max Act: 4.1206. Min Act: -0.1700
Data Index: 5983399 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.9956. Min Act: -0.1700
Data Index: 589593 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.8705. Min Act: -0.1700
Data Index: 6909379 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.7454. Min Act: -0.1700
Data Index: 6459764 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.7454. Min Act: -0.1700
Data Index: 3790507 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6985. Min Act: -0.1700
Data Index: 4168693 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6672. Min Act: -0.1700
Data Index: 7513943 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6516. Min Act: -0.1700
Data Index: 3237759 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6359. Min Act: -0.1700
Data Index: 8050847 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6203. Min Act: -0.1700
Data Index: 6517852 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6203. Min Act: -0.1700
Data Index: 144522 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6203. Min Act: -0.1700
Data Index: 7133598 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6046. Min Act: -0.1700
Data Index: 909231 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.6046. Min Act: -0.1700
Data Index: 3038615 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5890. Min Act: -0.1700
Data Index: 438687 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5890. Min Act: -0.1700
Data Index: 7569148 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5577. Min Act: -0.1700
Data Index: 7082346 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5733. Min Act: -0.1700
Data Index: 4733220 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5733. Min Act: -0.1700
Data Index: 1031823 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1206. Min Range: -4.1206
Max Act: 3.5733. Min Act: -0.1700
Data Index: 6969079 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19