Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2289. Min Range: -9.2289
Max Act: 9.2289. Min Act: -0.1700
Data Index: 779513 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.4789. Min Act: -0.1700
Data Index: 6974719 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.2914. Min Act: -0.1700
Data Index: 6473850 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.2289. Min Act: -0.1700
Data Index: 4433183 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.2289. Min Act: -0.1700
Data Index: 2782596 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.2289. Min Act: -0.1700
Data Index: 4115342 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.1664. Min Act: -0.1700
Data Index: 7233452 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.1351. Min Act: -0.1700
Data Index: 4147777 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.1039. Min Act: -0.1700
Data Index: 8476130 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.0414. Min Act: -0.1700
Data Index: 2051206 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2289. Min Range: -9.2289
Max Act: 8.0726. Min Act: -0.1700
Data Index: 8823419 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.8851. Min Act: -0.1700
Data Index: 4132528 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.8226. Min Act: -0.1700
Data Index: 3066486 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.8226. Min Act: -0.1700
Data Index: 7189823 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.7914. Min Act: -0.1700
Data Index: 3450003 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.7601. Min Act: -0.1700
Data Index: 238614 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.7289. Min Act: -0.1700
Data Index: 3310121 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.6976. Min Act: -0.1700
Data Index: 2550173 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.7289. Min Act: -0.1700
Data Index: 510755 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2289. Min Range: -9.2289
Max Act: 7.7289. Min Act: -0.1700
Data Index: 560736 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19