Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.5761. Min Act: -0.1700
Data Index: 4511173 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.5761. Min Act: -0.1700
Data Index: 3489254 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.5136. Min Act: -0.1700
Data Index: 4753232 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.4824. Min Act: -0.1700
Data Index: 7531629 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.4824. Min Act: -0.1700
Data Index: 3321236 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.4199. Min Act: -0.1700
Data Index: 4446957 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.4511. Min Act: -0.1700
Data Index: 388410 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.4199. Min Act: -0.1700
Data Index: 6256322 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3886. Min Act: -0.1700
Data Index: 959854 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3574. Min Act: -0.1700
Data Index: 6119004 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3574. Min Act: -0.1700
Data Index: 452234 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3661751 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3261. Min Act: -0.1700
Data Index: 430192 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.2949. Min Act: -0.1700
Data Index: 7221394 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3261. Min Act: -0.1700
Data Index: 871227 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.2949. Min Act: -0.1700
Data Index: 5639191 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.2949. Min Act: -0.1700
Data Index: 3444337 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.3261. Min Act: -0.1700
Data Index: 7405206 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.2636. Min Act: -0.1700
Data Index: 563883 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5761. Min Range: -4.5761
Max Act: 4.2949. Min Act: -0.1700
Data Index: 6290696 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19