Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.9163. Min Act: -0.1700
Data Index: 8235489 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.7601. Min Act: -0.1700
Data Index: 2412904 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.7288. Min Act: -0.1700
Data Index: 6690331 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.7288. Min Act: -0.1700
Data Index: 6783501 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6976. Min Act: -0.1700
Data Index: 5198635 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.7288. Min Act: -0.1700
Data Index: 5192765 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6976. Min Act: -0.1700
Data Index: 1853471 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6976. Min Act: -0.1700
Data Index: 5390036 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.7288. Min Act: -0.1700
Data Index: 1535837 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6663. Min Act: -0.1700
Data Index: 1616149 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6663. Min Act: -0.1700
Data Index: 1452741 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6038. Min Act: -0.1700
Data Index: 6861099 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6663. Min Act: -0.1700
Data Index: 5976679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6663. Min Act: -0.1700
Data Index: 6141230 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6351. Min Act: -0.1700
Data Index: 922808 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6351. Min Act: -0.1700
Data Index: 7553452 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6351. Min Act: -0.1700
Data Index: 2607091 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6351. Min Act: -0.1700
Data Index: 3444657 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6038. Min Act: -0.1700
Data Index: 773311 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9163. Min Range: -5.9163
Max Act: 5.6038. Min Act: -0.1700
Data Index: 5894405 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19