Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.1945. Min Act: -0.1700
Data Index: 8494142 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0695. Min Act: -0.1700
Data Index: 6309038 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 4028566 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 5424785 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1945. Min Range: -5.1945
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2247995 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9758. Min Act: -0.1700
Data Index: 5423761 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9758. Min Act: -0.1700
Data Index: 3739378 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8820. Min Act: -0.1700
Data Index: 8329132 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8820. Min Act: -0.1700
Data Index: 1502139 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8820. Min Act: -0.1700
Data Index: 5733612 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.9133. Min Act: -0.1700
Data Index: 8203672 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8820. Min Act: -0.1700
Data Index: 8503951 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8508. Min Act: -0.1700
Data Index: 6429555 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8508. Min Act: -0.1700
Data Index: 4884537 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8820. Min Act: -0.1700
Data Index: 1388577 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.8195. Min Act: -0.1700
Data Index: 6716600 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.7883. Min Act: -0.1700
Data Index: 2701765 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.7883. Min Act: -0.1700
Data Index: 6499829 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.7570. Min Act: -0.1700
Data Index: 3098671 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1945. Min Range: -5.1945
Max Act: 4.7570. Min Act: -0.1700
Data Index: 3016037 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19