Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.1275. Min Act: -0.1700
Data Index: 782247 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.0962. Min Act: -0.1700
Data Index: 4422167 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.0650. Min Act: -0.1700
Data Index: 5983168 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.0337. Min Act: -0.1700
Data Index: 5652806 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.0337. Min Act: -0.1700
Data Index: 2991535 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1275. Min Range: -8.1275
Max Act: 8.0337. Min Act: -0.1700
Data Index: 5983171 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.8462. Min Act: -0.1700
Data Index: 910312 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.8150. Min Act: -0.1700
Data Index: 2802894 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.7837. Min Act: -0.1700
Data Index: 332606 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.7525. Min Act: -0.1700
Data Index: 5551140 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.7525. Min Act: -0.1700
Data Index: 2533277 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.6900. Min Act: -0.1700
Data Index: 4902520 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.6587. Min Act: -0.1700
Data Index: 3170057 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.6275. Min Act: -0.1700
Data Index: 7591301 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.6275. Min Act: -0.1700
Data Index: 3619288 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.6587. Min Act: -0.1700
Data Index: 6529711 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.5650. Min Act: -0.1700
Data Index: 8125965 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.4400. Min Act: -0.1700
Data Index: 5617450 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.4712. Min Act: -0.1700
Data Index: 6724362 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1275. Min Range: -8.1275
Max Act: 7.4400. Min Act: -0.1700
Data Index: 5880111 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19