Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3658. Min Act: -0.1700
Data Index: 1160803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3658. Min Act: -0.1700
Data Index: 4276350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3345. Min Act: -0.1700
Data Index: 7159553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3345. Min Act: -0.1700
Data Index: 7992976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3188. Min Act: -0.1700
Data Index: 4737925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3188. Min Act: -0.1700
Data Index: 4624125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3031. Min Act: -0.1700
Data Index: 385207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.3031. Min Act: -0.1700
Data Index: 6501559 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2874. Min Act: -0.1700
Data Index: 1514455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2874. Min Act: -0.1700
Data Index: 7948009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2560. Min Act: -0.1700
Data Index: 6625655 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2717. Min Act: -0.1700
Data Index: 2356513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2717. Min Act: -0.1700
Data Index: 8763199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2717. Min Act: -0.1700
Data Index: 4045605 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2717. Min Act: -0.1700
Data Index: 4790765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2560. Min Act: -0.1700
Data Index: 4978809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2560. Min Act: -0.1700
Data Index: 1231018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2403. Min Act: -0.1700
Data Index: 2133091 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2403. Min Act: -0.1700
Data Index: 4669567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3658. Min Range: -3.3658
Max Act: 3.2403. Min Act: -0.1700
Data Index: 5258963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19