Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.3406. Min Act: -0.1700
Data Index: 3620691 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.3054. Min Act: -0.1700
Data Index: 8474302 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.3054. Min Act: -0.1700
Data Index: 381382 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2789. Min Act: -0.1700
Data Index: 7414718 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2877. Min Act: -0.1700
Data Index: 6466340 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2701. Min Act: -0.1700
Data Index: 6661924 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2789. Min Act: -0.1700
Data Index: 1787408 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 513456 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2524. Min Act: -0.1700
Data Index: 8441088 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2701. Min Act: -0.1700
Data Index: 1645130 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2701. Min Act: -0.1700
Data Index: 4006771 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2701. Min Act: -0.1700
Data Index: 8563263 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2524. Min Act: -0.1700
Data Index: 5996308 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 620340 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 5601690 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 6974586 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 4412151 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2436. Min Act: -0.1700
Data Index: 882 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2524. Min Act: -0.1700
Data Index: 1506256 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3406. Min Range: -1.3406
Max Act: 1.2613. Min Act: -0.1700
Data Index: 3681321 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19