Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0195. Min Range: -7.0195
Max Act: 7.0195. Min Act: -0.1700
Data Index: 4735695 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.8632. Min Act: -0.1700
Data Index: 3143551 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.8320. Min Act: -0.1700
Data Index: 3571025 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.7382. Min Act: -0.1700
Data Index: 6761034 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.7070. Min Act: -0.1700
Data Index: 880298 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.6445. Min Act: -0.1700
Data Index: 8696146 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.6445. Min Act: -0.1700
Data Index: 2919383 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.6132. Min Act: -0.1700
Data Index: 2384451 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.5507. Min Act: -0.1700
Data Index: 1306241 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.5195. Min Act: -0.1700
Data Index: 1176474 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.4882. Min Act: -0.1700
Data Index: 4280703 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.4570. Min Act: -0.1700
Data Index: 7389221 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.4882. Min Act: -0.1700
Data Index: 6583066 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.3945. Min Act: -0.1700
Data Index: 3344144 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.3945. Min Act: -0.1700
Data Index: 3636187 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.3320. Min Act: -0.1700
Data Index: 7306382 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.3320. Min Act: -0.1700
Data Index: 2533145 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.2695. Min Act: -0.1700
Data Index: 5956720 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.2695. Min Act: -0.1700
Data Index: 4361352 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0195. Min Range: -7.0195
Max Act: 6.2382. Min Act: -0.1700
Data Index: 1100005 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19