Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4077. Min Range: -7.4077
Max Act: 7.4077. Min Act: -0.1700
Data Index: 5765356 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4077. Min Range: -7.4077
Max Act: 7.3764. Min Act: -0.1700
Data Index: 589768 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4077. Min Range: -7.4077
Max Act: 7.0952. Min Act: -0.1700
Data Index: 2943828 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4077. Min Range: -7.4077
Max Act: 7.1264. Min Act: -0.1700
Data Index: 3026248 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4077. Min Range: -7.4077
Max Act: 7.0014. Min Act: -0.1700
Data Index: 1538745 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.9389. Min Act: -0.1700
Data Index: 4516250 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.9077. Min Act: -0.1700
Data Index: 215515 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.8452. Min Act: -0.1700
Data Index: 376515 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.8452. Min Act: -0.1700
Data Index: 667790 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.8452. Min Act: -0.1700
Data Index: 4115299 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.8139. Min Act: -0.1700
Data Index: 4438517 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6237573 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.7202. Min Act: -0.1700
Data Index: 7232201 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.7202. Min Act: -0.1700
Data Index: 2706379 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.7202. Min Act: -0.1700
Data Index: 5874261 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.7202. Min Act: -0.1700
Data Index: 761945 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.6577. Min Act: -0.1700
Data Index: 1207045 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.6577. Min Act: -0.1700
Data Index: 342177 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.6889. Min Act: -0.1700
Data Index: 1911893 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4077. Min Range: -7.4077
Max Act: 6.6264. Min Act: -0.1700
Data Index: 5735228 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19