Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5809 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2863. Min Act: -0.1700
Data Index: 3949259 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 5939378 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.2234. Min Act: -0.1700
Data Index: 5613650 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1920. Min Act: -0.1700
Data Index: 599763 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1448. Min Act: -0.1700
Data Index: 3155681 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1290. Min Act: -0.1700
Data Index: 1105561 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1290. Min Act: -0.1700
Data Index: 5430511 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1290. Min Act: -0.1700
Data Index: 5392401 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1290. Min Act: -0.1700
Data Index: 4329879 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.1133. Min Act: -0.1700
Data Index: 925270 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0975. Min Act: -0.1700
Data Index: 390229 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0975. Min Act: -0.1700
Data Index: 3367771 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0975. Min Act: -0.1700
Data Index: 4277266 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0660. Min Act: -0.1700
Data Index: 2429502 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0660. Min Act: -0.1700
Data Index: 4573579 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0502. Min Act: -0.1700
Data Index: 4989302 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0344. Min Act: -0.1700
Data Index: 2786766 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0344. Min Act: -0.1700
Data Index: 7034167 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0186. Min Act: -0.1700
Data Index: 2689151 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2863. Min Range: -3.2863
Max Act: 3.0186. Min Act: -0.1700
Data Index: 1448531 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19