Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2168. Min Range: -6.2168
Max Act: 6.2168. Min Act: -0.1700
Data Index: 6830168 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2168. Min Range: -6.2168
Max Act: 6.0293. Min Act: -0.1700
Data Index: 2158105 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.9043. Min Act: -0.1700
Data Index: 8009694 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.8418. Min Act: -0.1700
Data Index: 213154 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.8730. Min Act: -0.1700
Data Index: 1938797 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4910094 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.6543. Min Act: -0.1700
Data Index: 3784443 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.6543. Min Act: -0.1700
Data Index: 1783503 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.6543. Min Act: -0.1700
Data Index: 249269 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6886107 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.5918. Min Act: -0.1700
Data Index: 3761332 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.6230. Min Act: -0.1700
Data Index: 957383 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.5605. Min Act: -0.1700
Data Index: 6021908 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 7391116 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 3763763 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.4980. Min Act: -0.1700
Data Index: 1389578 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.4980. Min Act: -0.1700
Data Index: 1167164 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.4980. Min Act: -0.1700
Data Index: 4175196 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.4980. Min Act: -0.1700
Data Index: 498416 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2168. Min Range: -6.2168
Max Act: 5.4980. Min Act: -0.1700
Data Index: 5265238 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19