Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.3623. Min Act: -0.1700
Data Index: 4266575 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1748. Min Act: -0.1700
Data Index: 2751753 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1748. Min Act: -0.1700
Data Index: 276271 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.2060. Min Act: -0.1700
Data Index: 7758367 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1435. Min Act: -0.1700
Data Index: 4279939 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1435. Min Act: -0.1700
Data Index: 315070 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1123. Min Act: -0.1700
Data Index: 722011 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0498. Min Act: -0.1700
Data Index: 1180871 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1123. Min Act: -0.1700
Data Index: 5833583 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.1123. Min Act: -0.1700
Data Index: 1638620 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0498. Min Act: -0.1700
Data Index: 2600583 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0810. Min Act: -0.1700
Data Index: 7654818 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3623. Min Range: -6.3623
Max Act: 5.9873. Min Act: -0.1700
Data Index: 4894404 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0185. Min Act: -0.1700
Data Index: 3183949 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0185. Min Act: -0.1700
Data Index: 7496578 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3623. Min Range: -6.3623
Max Act: 5.9873. Min Act: -0.1700
Data Index: 5535918 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3623. Min Range: -6.3623
Max Act: 6.0185. Min Act: -0.1700
Data Index: 4432945 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3623. Min Range: -6.3623
Max Act: 5.9873. Min Act: -0.1700
Data Index: 2193317 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3623. Min Range: -6.3623
Max Act: 5.9873. Min Act: -0.1700
Data Index: 958619 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3623. Min Range: -6.3623
Max Act: 5.9560. Min Act: -0.1700
Data Index: 5319437 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19