Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.5915. Min Act: -0.1700
Data Index: 3249283 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.5445. Min Act: -0.1700
Data Index: 4932968 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.5132. Min Act: -0.1700
Data Index: 1272740 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4819. Min Act: -0.1700
Data Index: 5708639 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4975. Min Act: -0.1700
Data Index: 7120445 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4348. Min Act: -0.1700
Data Index: 7780871 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4505. Min Act: -0.1700
Data Index: 8769127 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4505. Min Act: -0.1700
Data Index: 8032435 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4505. Min Act: -0.1700
Data Index: 1319400 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.4192. Min Act: -0.1700
Data Index: 6530431 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3878. Min Act: -0.1700
Data Index: 178835 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3878. Min Act: -0.1700
Data Index: 5638248 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3878. Min Act: -0.1700
Data Index: 8270463 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3721. Min Act: -0.1700
Data Index: 4963346 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3721. Min Act: -0.1700
Data Index: 2145062 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3721. Min Act: -0.1700
Data Index: 2561001 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3564. Min Act: -0.1700
Data Index: 5353941 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3251. Min Act: -0.1700
Data Index: 2761426 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3094. Min Act: -0.1700
Data Index: 2656223 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5915. Min Range: -3.5915
Max Act: 3.3408. Min Act: -0.1700
Data Index: 2360368 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19