Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.6944. Min Act: -0.1700
Data Index: 1958151 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.7257. Min Act: -0.1700
Data Index: 109509 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.6319. Min Act: -0.1700
Data Index: 4770147 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.6007. Min Act: -0.1700
Data Index: 2802503 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.5694. Min Act: -0.1700
Data Index: 541295 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.5382. Min Act: -0.1700
Data Index: 2010939 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 4352932 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.5069. Min Act: -0.1700
Data Index: 2136742 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.5069. Min Act: -0.1700
Data Index: 5849806 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.5382. Min Act: -0.1700
Data Index: 5640877 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 8536435 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 3525578 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 3341577 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 6255498 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 7883422 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 2023541 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4757. Min Act: -0.1700
Data Index: 7519811 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4444. Min Act: -0.1700
Data Index: 4803333 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4444. Min Act: -0.1700
Data Index: 1386436 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7257. Min Range: -4.7257
Max Act: 4.4131. Min Act: -0.1700
Data Index: 6146459 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19