Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.6005. Min Act: -0.1700
Data Index: 3755145 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.4442. Min Act: -0.1700
Data Index: 1660964 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.4442. Min Act: -0.1700
Data Index: 5977818 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.4442. Min Act: -0.1700
Data Index: 4927631 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.3817. Min Act: -0.1700
Data Index: 6180545 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.3505. Min Act: -0.1700
Data Index: 8115719 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.3192. Min Act: -0.1700
Data Index: 7680371 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.3505. Min Act: -0.1700
Data Index: 3533098 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.2880. Min Act: -0.1700
Data Index: 8216966 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.2880. Min Act: -0.1700
Data Index: 3173102 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.2880. Min Act: -0.1700
Data Index: 8033068 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.2255. Min Act: -0.1700
Data Index: 697402 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1942. Min Act: -0.1700
Data Index: 6201865 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1942. Min Act: -0.1700
Data Index: 8430449 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1942. Min Act: -0.1700
Data Index: 4175806 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.2255. Min Act: -0.1700
Data Index: 4241914 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1942. Min Act: -0.1700
Data Index: 7212482 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1629. Min Act: -0.1700
Data Index: 4705516 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1317. Min Act: -0.1700
Data Index: 5802882 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6005. Min Range: -4.6005
Max Act: 4.1317. Min Act: -0.1700
Data Index: 7280730 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19