Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0163. Min Range: -5.0163
Max Act: 5.0163. Min Act: -0.1700
Data Index: 1081008 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5133597 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.7663. Min Act: -0.1700
Data Index: 6743571 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.4538. Min Act: -0.1700
Data Index: 8249136 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.4538. Min Act: -0.1700
Data Index: 4851999 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.4225. Min Act: -0.1700
Data Index: 8759068 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.4225. Min Act: -0.1700
Data Index: 7896436 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.4225. Min Act: -0.1700
Data Index: 4901225 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3912. Min Act: -0.1700
Data Index: 1113179 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3912. Min Act: -0.1700
Data Index: 4435809 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3912. Min Act: -0.1700
Data Index: 6925695 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3912. Min Act: -0.1700
Data Index: 3601030 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3287. Min Act: -0.1700
Data Index: 5780201 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2079673 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3912. Min Act: -0.1700
Data Index: 5274759 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2530422 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2803633 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3287. Min Act: -0.1700
Data Index: 7087650 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.2975. Min Act: -0.1700
Data Index: 1041763 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.3287. Min Act: -0.1700
Data Index: 6802329 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19