Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5532 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.6532. Min Act: -0.1700
Data Index: 6777498 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.6219. Min Act: -0.1700
Data Index: 1252820 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.4969. Min Act: -0.1700
Data Index: 8566610 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.4344. Min Act: -0.1700
Data Index: 8344474 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.3719. Min Act: -0.1700
Data Index: 5577548 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.2782. Min Act: -0.1700
Data Index: 373705 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.2469. Min Act: -0.1700
Data Index: 6777499 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.2469. Min Act: -0.1700
Data Index: 7274059 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.2469. Min Act: -0.1700
Data Index: 1042070 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1844. Min Act: -0.1700
Data Index: 893068 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1844. Min Act: -0.1700
Data Index: 4585531 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1532. Min Act: -0.1700
Data Index: 2020702 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1219. Min Act: -0.1700
Data Index: 5689022 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5567647 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1219. Min Act: -0.1700
Data Index: 1042074 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.1219. Min Act: -0.1700
Data Index: 1487948 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.0907. Min Act: -0.1700
Data Index: 4971700 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.0907. Min Act: -0.1700
Data Index: 4974554 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.0907. Min Act: -0.1700
Data Index: 7014265 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6532. Min Range: -5.6532
Max Act: 5.0907. Min Act: -0.1700
Data Index: 7652644 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19