Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1703. Min Range: -9.1703
Max Act: 9.1703. Min Act: -0.1700
Data Index: 3052972 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1703. Min Range: -9.1703
Max Act: 8.9203. Min Act: -0.1700
Data Index: 3052968 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1703. Min Range: -9.1703
Max Act: 8.4828. Min Act: -0.1700
Data Index: 7717337 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.9203. Min Act: -0.1700
Data Index: 240033 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.9203. Min Act: -0.1700
Data Index: 3618501 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.7953. Min Act: -0.1700
Data Index: 3904951 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.7953. Min Act: -0.1700
Data Index: 3532557 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.7953. Min Act: -0.1700
Data Index: 2509805 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.7328. Min Act: -0.1700
Data Index: 642327 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.7328. Min Act: -0.1700
Data Index: 2537626 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.6703. Min Act: -0.1700
Data Index: 4971121 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.6703. Min Act: -0.1700
Data Index: 4567462 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.6703. Min Act: -0.1700
Data Index: 5497772 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.6078. Min Act: -0.1700
Data Index: 6553685 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.6078. Min Act: -0.1700
Data Index: 2813826 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.5453. Min Act: -0.1700
Data Index: 2183133 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.5140. Min Act: -0.1700
Data Index: 5545307 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.5140. Min Act: -0.1700
Data Index: 4401578 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.5140. Min Act: -0.1700
Data Index: 6830156 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1703. Min Range: -9.1703
Max Act: 7.4515. Min Act: -0.1700
Data Index: 8543669 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19