Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.2647. Min Act: -0.1700
Data Index: 5329988 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.2118. Min Act: -0.1700
Data Index: 3920156 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1942. Min Act: -0.1700
Data Index: 7618932 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1942. Min Act: -0.1700
Data Index: 1275866 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1766. Min Act: -0.1700
Data Index: 2157588 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1415. Min Act: -0.1700
Data Index: 7829115 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1415. Min Act: -0.1700
Data Index: 7407301 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1239. Min Act: -0.1700
Data Index: 8462625 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 1275867 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 3941555 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 5266739 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 1355959 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0889. Min Act: -0.1700
Data Index: 2262513 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 6302192 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.1064. Min Act: -0.1700
Data Index: 6495489 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0889. Min Act: -0.1700
Data Index: 6482003 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0889. Min Act: -0.1700
Data Index: 6311920 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0714. Min Act: -0.1700
Data Index: 7488847 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0714. Min Act: -0.1700
Data Index: 5967788 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2647. Min Range: -1.2647
Max Act: 1.0889. Min Act: -0.1700
Data Index: 6646296 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19