Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.8494. Min Act: -0.1700
Data Index: 7923347 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.8151. Min Act: -0.1700
Data Index: 5513984 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7979. Min Act: -0.1700
Data Index: 3631125 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7979. Min Act: -0.1700
Data Index: 5257180 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7893. Min Act: -0.1700
Data Index: 4381467 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7548. Min Act: -0.1700
Data Index: 330753 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7635. Min Act: -0.1700
Data Index: 3461901 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7548. Min Act: -0.1700
Data Index: 447711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7548. Min Act: -0.1699
Data Index: 1189663 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7548. Min Act: -0.1700
Data Index: 6812144 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7548. Min Act: -0.1700
Data Index: 1748413 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7376. Min Act: -0.1700
Data Index: 7983026 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7376. Min Act: -0.1700
Data Index: 546540 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7462. Min Act: -0.1700
Data Index: 7094620 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7376. Min Act: -0.1700
Data Index: 6599885 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7289. Min Act: -0.1698
Data Index: 6552155 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7462. Min Act: -0.1700
Data Index: 3329158 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7462. Min Act: -0.1700
Data Index: 2212991 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7289. Min Act: -0.1700
Data Index: 6404500 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8494. Min Range: -1.8494
Max Act: 1.7203. Min Act: -0.1700
Data Index: 1514552 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19