Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 626 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3574. Min Range: -6.3574
Max Act: 6.3574. Min Act: -0.1700
Data Index: 7516799 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3574. Min Range: -6.3574
Max Act: 6.2636. Min Act: -0.1700
Data Index: 602253 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3574. Min Range: -6.3574
Max Act: 6.1074. Min Act: -0.1700
Data Index: 2918010 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3574. Min Range: -6.3574
Max Act: 6.0136. Min Act: -0.1700
Data Index: 5910155 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.9511. Min Act: -0.1700
Data Index: 5974276 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.9199. Min Act: -0.1700
Data Index: 7024087 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.8886. Min Act: -0.1700
Data Index: 2304648 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.8574. Min Act: -0.1700
Data Index: 2205446 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.8261. Min Act: -0.1700
Data Index: 8266984 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.8261. Min Act: -0.1700
Data Index: 7898923 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.8261. Min Act: -0.1700
Data Index: 6693657 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7949. Min Act: -0.1700
Data Index: 3354865 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4241865 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7949. Min Act: -0.1700
Data Index: 6105750 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3623254 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3597605 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7636. Min Act: -0.1700
Data Index: 4994660 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7324. Min Act: -0.1700
Data Index: 2417583 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7324. Min Act: -0.1700
Data Index: 2116538 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3574. Min Range: -6.3574
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6212816 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19