Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.3120. Min Act: -0.1700
Data Index: 957357 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.2495. Min Act: -0.1700
Data Index: 815428 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6744393 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.1245. Min Act: -0.1700
Data Index: 3463909 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2567023 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0932. Min Act: -0.1700
Data Index: 2494289 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0932. Min Act: -0.1700
Data Index: 3365163 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0932. Min Act: -0.1700
Data Index: 1907083 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0932. Min Act: -0.1700
Data Index: 8165848 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0620. Min Act: -0.1700
Data Index: 3517191 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0620. Min Act: -0.1700
Data Index: 5404026 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0620. Min Act: -0.1700
Data Index: 1884389 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0620. Min Act: -0.1700
Data Index: 748383 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0620. Min Act: -0.1700
Data Index: 3375518 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0307. Min Act: -0.1700
Data Index: 5267188 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3120. Min Range: -6.3120
Max Act: 5.9995. Min Act: -0.1700
Data Index: 6019370 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0307. Min Act: -0.1700
Data Index: 201366 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0307. Min Act: -0.1700
Data Index: 5362220 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0307. Min Act: -0.1696
Data Index: 7874154 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3120. Min Range: -6.3120
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2274640 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19