Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.6215. Min Act: -0.1700
Data Index: 7564531 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.5903. Min Act: -0.1700
Data Index: 7204337 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.5278. Min Act: -0.1700
Data Index: 5802954 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.4340. Min Act: -0.1700
Data Index: 2765697 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.4340. Min Act: -0.1700
Data Index: 6416201 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.3715. Min Act: -0.1700
Data Index: 1978081 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.3403. Min Act: -0.1700
Data Index: 753050 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.3715. Min Act: -0.1700
Data Index: 4321744 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.3090. Min Act: -0.1700
Data Index: 6443884 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.3090. Min Act: -0.1700
Data Index: 4157327 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2778. Min Act: -0.1700
Data Index: 4828223 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2778. Min Act: -0.1700
Data Index: 4242596 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2778. Min Act: -0.1700
Data Index: 5009320 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2778. Min Act: -0.1700
Data Index: 43658 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2778. Min Act: -0.1700
Data Index: 6983938 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2465. Min Act: -0.1700
Data Index: 6125459 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2465. Min Act: -0.1700
Data Index: 4962667 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2465. Min Act: -0.1700
Data Index: 6444129 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2153. Min Act: -0.1700
Data Index: 2297892 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6215. Min Range: -5.6215
Max Act: 5.2153. Min Act: -0.1700
Data Index: 2487697 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19